Merge branches 'doc.2013.08.19a', 'fixes.2013.08.20a', 'sysidle.2013.08.31a' and 'torture.2013.08.20a' into HEAD

doc.2013.08.19a: Documentation updates
fixes.2013.08.20a: Miscellaneous fixes
sysidle.2013.08.31a: Detect system-wide idle state.
torture.2013.08.20a: rcutorture updates.

Documentation/RCU/torture.txt

···
 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/timers/NO_HZ.txt

···
 	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
···
 "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
···
 pin the "rcuo" kthreads to specific CPUs if desired.  Otherwise, the
 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

include/linux/debugobjects.h

···
 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);
···
 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/jiffies.h

···
 #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)
 
 /*
···
 #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

···
  */
 #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

···
 #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 */
···
 #else
 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 */

init/Kconfig

···
 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

···
 
 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)
···
 	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)

kernel/rcupdate.c

···
 }
 
 /*
- * 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
  * - an unknown object is activated (might be a statically initialized object)
···
 		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;
 	}
 }
 
···
 
 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 */

kernel/rcutorture.c

···
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <[e-mail]> and Josh Triplett <[e-mail]>");
 
-static int nreaders = -1;	/* # reader threads, defaults to 2*ncpus */
-static int nfakewriters = 4;	/* # fake writer threads */
-static int stat_interval = 60;	/* Interval between stats, in seconds. */
-				/*  Zero means "only at end of test". */
-static bool verbose;		/* Print more debug info. */
-static bool test_no_idle_hz = true;
-				/* Test RCU support for tickless idle CPUs. */
-static int shuffle_interval = 3; /* Interval between shuffles (in sec)*/
-static int stutter = 5;		/* Start/stop testing interval (in sec) */
-static int irqreader = 1;	/* RCU readers from irq (timers). */
-static int fqs_duration;	/* Duration of bursts (us), 0 to disable. */
-static int fqs_holdoff;		/* Hold time within burst (us). */
-static int fqs_stutter = 3;	/* Wait time between bursts (s). */
-static int n_barrier_cbs;	/* Number of callbacks to test RCU barriers. */
-static int onoff_interval;	/* Wait time between CPU hotplugs, 0=disable. */
-static int onoff_holdoff;	/* Seconds after boot before CPU hotplugs. */
-static int shutdown_secs;	/* Shutdown time (s).  <=0 for no shutdown. */
-static int stall_cpu;		/* CPU-stall duration (s).  0 for no stall. */
-static int stall_cpu_holdoff = 10; /* Time to wait until stall (s).  */
-static int test_boost = 1;	/* Test RCU prio boost: 0=no, 1=maybe, 2=yes. */
-static int test_boost_interval = 7; /* Interval between boost tests, seconds. */
-static int test_boost_duration = 4; /* Duration of each boost test, seconds. */
-static char *torture_type = "rcu"; /* What RCU implementation to torture. */
-
-module_param(nreaders, int, 0444);
-MODULE_PARM_DESC(nreaders, "Number of RCU reader threads");
-module_param(nfakewriters, int, 0444);
-MODULE_PARM_DESC(nfakewriters, "Number of RCU fake writer threads");
-module_param(stat_interval, int, 0644);
-MODULE_PARM_DESC(stat_interval, "Number of seconds between stats printk()s");
-module_param(verbose, bool, 0444);
-MODULE_PARM_DESC(verbose, "Enable verbose debugging printk()s");
-module_param(test_no_idle_hz, bool, 0444);
-MODULE_PARM_DESC(test_no_idle_hz, "Test support for tickless idle CPUs");
-module_param(shuffle_interval, int, 0444);
-MODULE_PARM_DESC(shuffle_interval, "Number of seconds between shuffles");
-module_param(stutter, int, 0444);
-MODULE_PARM_DESC(stutter, "Number of seconds to run/halt test");
-module_param(irqreader, int, 0444);
-MODULE_PARM_DESC(irqreader, "Allow RCU readers from irq handlers");
+static int fqs_duration;
 module_param(fqs_duration, int, 0444);
-MODULE_PARM_DESC(fqs_duration, "Duration of fqs bursts (us)");
+MODULE_PARM_DESC(fqs_duration, "Duration of fqs bursts (us), 0 to disable");
+static int fqs_holdoff;
 module_param(fqs_holdoff, int, 0444);
 MODULE_PARM_DESC(fqs_holdoff, "Holdoff time within fqs bursts (us)");
+static int fqs_stutter = 3;
 module_param(fqs_stutter, int, 0444);
 MODULE_PARM_DESC(fqs_stutter, "Wait time between fqs bursts (s)");
+static bool gp_exp;
+module_param(gp_exp, bool, 0444);
+MODULE_PARM_DESC(gp_exp, "Use expedited GP wait primitives");
+static bool gp_normal;
+module_param(gp_normal, bool, 0444);
+MODULE_PARM_DESC(gp_normal, "Use normal (non-expedited) GP wait primitives");
+static int irqreader = 1;
+module_param(irqreader, int, 0444);
+MODULE_PARM_DESC(irqreader, "Allow RCU readers from irq handlers");
+static int n_barrier_cbs;
 module_param(n_barrier_cbs, int, 0444);
 MODULE_PARM_DESC(n_barrier_cbs, "# of callbacks/kthreads for barrier testing");
-module_param(onoff_interval, int, 0444);
-MODULE_PARM_DESC(onoff_interval, "Time between CPU hotplugs (s), 0=disable");
+static int nfakewriters = 4;
+module_param(nfakewriters, int, 0444);
+MODULE_PARM_DESC(nfakewriters, "Number of RCU fake writer threads");
+static int nreaders = -1;
+module_param(nreaders, int, 0444);
+MODULE_PARM_DESC(nreaders, "Number of RCU reader threads");
+static int object_debug;
+module_param(object_debug, int, 0444);
+MODULE_PARM_DESC(object_debug, "Enable debug-object double call_rcu() testing");
+static int onoff_holdoff;
 module_param(onoff_holdoff, int, 0444);
 MODULE_PARM_DESC(onoff_holdoff, "Time after boot before CPU hotplugs (s)");
+static int onoff_interval;
+module_param(onoff_interval, int, 0444);
+MODULE_PARM_DESC(onoff_interval, "Time between CPU hotplugs (s), 0=disable");
+static int shuffle_interval = 3;
+module_param(shuffle_interval, int, 0444);
+MODULE_PARM_DESC(shuffle_interval, "Number of seconds between shuffles");
+static int shutdown_secs;
 module_param(shutdown_secs, int, 0444);
-MODULE_PARM_DESC(shutdown_secs, "Shutdown time (s), zero to disable.");
+MODULE_PARM_DESC(shutdown_secs, "Shutdown time (s), <= zero to disable.");
+static int stall_cpu;
 module_param(stall_cpu, int, 0444);
 MODULE_PARM_DESC(stall_cpu, "Stall duration (s), zero to disable.");
+static int stall_cpu_holdoff = 10;
 module_param(stall_cpu_holdoff, int, 0444);
 MODULE_PARM_DESC(stall_cpu_holdoff, "Time to wait before starting stall (s).");
+static int stat_interval = 60;
+module_param(stat_interval, int, 0644);
+MODULE_PARM_DESC(stat_interval, "Number of seconds between stats printk()s");
+static int stutter = 5;
+module_param(stutter, int, 0444);
+MODULE_PARM_DESC(stutter, "Number of seconds to run/halt test");
+static int test_boost = 1;
 module_param(test_boost, int, 0444);
 MODULE_PARM_DESC(test_boost, "Test RCU prio boost: 0=no, 1=maybe, 2=yes.");
-module_param(test_boost_interval, int, 0444);
-MODULE_PARM_DESC(test_boost_interval, "Interval between boost tests, seconds.");
+static int test_boost_duration = 4;
 module_param(test_boost_duration, int, 0444);
 MODULE_PARM_DESC(test_boost_duration, "Duration of each boost test, seconds.");
+static int test_boost_interval = 7;
+module_param(test_boost_interval, int, 0444);
+MODULE_PARM_DESC(test_boost_interval, "Interval between boost tests, seconds.");
+static bool test_no_idle_hz = true;
+module_param(test_no_idle_hz, bool, 0444);
+MODULE_PARM_DESC(test_no_idle_hz, "Test support for tickless idle CPUs");
+static char *torture_type = "rcu";
 module_param(torture_type, charp, 0444);
-MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, srcu)");
+MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, ...)");
+static bool verbose;
+module_param(verbose, bool, 0444);
+MODULE_PARM_DESC(verbose, "Enable verbose debugging printk()s");
 
 #define TORTURE_FLAG "-torture:"
 #define PRINTK_STRING(s) \
···
 	int (*completed)(void);
 	void (*deferred_free)(struct rcu_torture *p);
 	void (*sync)(void);
+	void (*exp_sync)(void);
 	void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
 	void (*cb_barrier)(void);
 	void (*fqs)(void);
···
 	call_rcu(&p->rtort_rcu, rcu_torture_cb);
 }
 
+static void rcu_sync_torture_init(void)
+{
+	INIT_LIST_HEAD(&rcu_torture_removed);
+}
+
 static struct rcu_torture_ops rcu_ops = {
-	.init		= NULL,
+	.init		= rcu_sync_torture_init,
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,
 	.readunlock	= rcu_torture_read_unlock,
 	.completed	= rcu_torture_completed,
 	.deferred_free	= rcu_torture_deferred_free,
 	.sync		= synchronize_rcu,
+	.exp_sync	= synchronize_rcu_expedited,
 	.call		= call_rcu,
 	.cb_barrier	= rcu_barrier,
 	.fqs		= rcu_force_quiescent_state,
···
 	.irq_capable	= 1,
 	.can_boost	= rcu_can_boost(),
 	.name		= "rcu"
-};
-
-static void rcu_sync_torture_deferred_free(struct rcu_torture *p)
-{
-	int i;
-	struct rcu_torture *rp;
-	struct rcu_torture *rp1;
-
-	cur_ops->sync();
-	list_add(&p->rtort_free, &rcu_torture_removed);
-	list_for_each_entry_safe(rp, rp1, &rcu_torture_removed, rtort_free) {
-		i = rp->rtort_pipe_count;
-		if (i > RCU_TORTURE_PIPE_LEN)
-			i = RCU_TORTURE_PIPE_LEN;
-		atomic_inc(&rcu_torture_wcount[i]);
-		if (++rp->rtort_pipe_count >= RCU_TORTURE_PIPE_LEN) {
-			rp->rtort_mbtest = 0;
-			list_del(&rp->rtort_free);
-			rcu_torture_free(rp);
-		}
-	}
-}
-
-static void rcu_sync_torture_init(void)
-{
-	INIT_LIST_HEAD(&rcu_torture_removed);
-}
-
-static struct rcu_torture_ops rcu_sync_ops = {
-	.init		= rcu_sync_torture_init,
-	.readlock	= rcu_torture_read_lock,
-	.read_delay	= rcu_read_delay,
-	.readunlock	= rcu_torture_read_unlock,
-	.completed	= rcu_torture_completed,
-	.deferred_free	= rcu_sync_torture_deferred_free,
-	.sync		= synchronize_rcu,
-	.call		= NULL,
-	.cb_barrier	= NULL,
-	.fqs		= rcu_force_quiescent_state,
-	.stats		= NULL,
-	.irq_capable	= 1,
-	.can_boost	= rcu_can_boost(),
-	.name		= "rcu_sync"
-};
-
-static struct rcu_torture_ops rcu_expedited_ops = {
-	.init		= rcu_sync_torture_init,
-	.readlock	= rcu_torture_read_lock,
-	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock	= rcu_torture_read_unlock,
-	.completed	= rcu_no_completed,
-	.deferred_free	= rcu_sync_torture_deferred_free,
-	.sync		= synchronize_rcu_expedited,
-	.call		= NULL,
-	.cb_barrier	= NULL,
-	.fqs		= rcu_force_quiescent_state,
-	.stats		= NULL,
-	.irq_capable	= 1,
-	.can_boost	= rcu_can_boost(),
-	.name		= "rcu_expedited"
 };
 
 /*
···
 }
 
 static struct rcu_torture_ops rcu_bh_ops = {
-	.init		= NULL,
+	.init		= rcu_sync_torture_init,
 	.readlock	= rcu_bh_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_bh_torture_read_unlock,
 	.completed	= rcu_bh_torture_completed,
 	.deferred_free	= rcu_bh_torture_deferred_free,
 	.sync		= synchronize_rcu_bh,
+	.exp_sync	= synchronize_rcu_bh_expedited,
 	.call		= call_rcu_bh,
 	.cb_barrier	= rcu_barrier_bh,
 	.fqs		= rcu_bh_force_quiescent_state,
 	.stats		= NULL,
 	.irq_capable	= 1,
 	.name		= "rcu_bh"
-};
-
-static struct rcu_torture_ops rcu_bh_sync_ops = {
-	.init		= rcu_sync_torture_init,
-	.readlock	= rcu_bh_torture_read_lock,
-	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock	= rcu_bh_torture_read_unlock,
-	.completed	= rcu_bh_torture_completed,
-	.deferred_free	= rcu_sync_torture_deferred_free,
-	.sync		= synchronize_rcu_bh,
-	.call		= NULL,
-	.cb_barrier	= NULL,
-	.fqs		= rcu_bh_force_quiescent_state,
-	.stats		= NULL,
-	.irq_capable	= 1,
-	.name		= "rcu_bh_sync"
-};
-
-static struct rcu_torture_ops rcu_bh_expedited_ops = {
-	.init		= rcu_sync_torture_init,
-	.readlock	= rcu_bh_torture_read_lock,
-	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock	= rcu_bh_torture_read_unlock,
-	.completed	= rcu_bh_torture_completed,
-	.deferred_free	= rcu_sync_torture_deferred_free,
-	.sync		= synchronize_rcu_bh_expedited,
-	.call		= NULL,
-	.cb_barrier	= NULL,
-	.fqs		= rcu_bh_force_quiescent_state,
-	.stats		= NULL,
-	.irq_capable	= 1,
-	.name		= "rcu_bh_expedited"
 };
 
 /*
···
 	return cnt;
 }
 
+static void srcu_torture_synchronize_expedited(void)
+{
+	synchronize_srcu_expedited(&srcu_ctl);
+}
+
 static struct rcu_torture_ops srcu_ops = {
 	.init		= rcu_sync_torture_init,
 	.readlock	= srcu_torture_read_lock,
···
 	.completed	= srcu_torture_completed,
 	.deferred_free	= srcu_torture_deferred_free,
 	.sync		= srcu_torture_synchronize,
+	.exp_sync	= srcu_torture_synchronize_expedited,
 	.call		= srcu_torture_call,
 	.cb_barrier	= srcu_torture_barrier,
 	.stats		= srcu_torture_stats,
 	.name		= "srcu"
-};
-
-static struct rcu_torture_ops srcu_sync_ops = {
-	.init		= rcu_sync_torture_init,
-	.readlock	= srcu_torture_read_lock,
-	.read_delay	= srcu_read_delay,
-	.readunlock	= srcu_torture_read_unlock,
-	.completed	= srcu_torture_completed,
-	.deferred_free	= rcu_sync_torture_deferred_free,
-	.sync		= srcu_torture_synchronize,
-	.call		= NULL,
-	.cb_barrier	= NULL,
-	.stats		= srcu_torture_stats,
-	.name		= "srcu_sync"
-};
-
-static void srcu_torture_synchronize_expedited(void)
-{
-	synchronize_srcu_expedited(&srcu_ctl);
-}
-
-static struct rcu_torture_ops srcu_expedited_ops = {
-	.init		= rcu_sync_torture_init,
-	.readlock	= srcu_torture_read_lock,
-	.read_delay	= srcu_read_delay,
-	.readunlock	= srcu_torture_read_unlock,
-	.completed	= srcu_torture_completed,
-	.deferred_free	= rcu_sync_torture_deferred_free,
-	.sync		= srcu_torture_synchronize_expedited,
-	.call		= NULL,
-	.cb_barrier	= NULL,
-	.stats		= srcu_torture_stats,
-	.name		= "srcu_expedited"
 };
 
 /*
···
 	.completed	= rcu_no_completed,
 	.deferred_free	= rcu_sched_torture_deferred_free,
 	.sync		= synchronize_sched,
+	.exp_sync	= synchronize_sched_expedited,
+	.call		= call_rcu_sched,
 	.cb_barrier	= rcu_barrier_sched,
 	.fqs		= rcu_sched_force_quiescent_state,
 	.stats		= NULL,
 	.irq_capable	= 1,
 	.name		= "sched"
-};
-
-static struct rcu_torture_ops sched_sync_ops = {
-	.init		= rcu_sync_torture_init,
-	.readlock	= sched_torture_read_lock,
-	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock	= sched_torture_read_unlock,
-	.completed	= rcu_no_completed,
-	.deferred_free	= rcu_sync_torture_deferred_free,
-	.sync		= synchronize_sched,
-	.cb_barrier	= NULL,
-	.fqs		= rcu_sched_force_quiescent_state,
-	.stats		= NULL,
-	.name		= "sched_sync"
-};
-
-static struct rcu_torture_ops sched_expedited_ops = {
-	.init		= rcu_sync_torture_init,
-	.readlock	= sched_torture_read_lock,
-	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
-	.readunlock	= sched_torture_read_unlock,
-	.completed	= rcu_no_completed,
-	.deferred_free	= rcu_sync_torture_deferred_free,
-	.sync		= synchronize_sched_expedited,
-	.cb_barrier	= NULL,
-	.fqs		= rcu_sched_force_quiescent_state,
-	.stats		= NULL,
-	.irq_capable	= 1,
-	.name		= "sched_expedited"
 };
 
 /*
···
 static int
 rcu_torture_writer(void *arg)
 {
+	bool exp;
 	int i;
-	long oldbatch = rcu_batches_completed();
 	struct rcu_torture *rp;
+	struct rcu_torture *rp1;
 	struct rcu_torture *old_rp;
 	static DEFINE_RCU_RANDOM(rand);
 
···
 				i = RCU_TORTURE_PIPE_LEN;
 			atomic_inc(&rcu_torture_wcount[i]);
 			old_rp->rtort_pipe_count++;
-			cur_ops->deferred_free(old_rp);
+			if (gp_normal == gp_exp)
+				exp = !!(rcu_random(&rand) & 0x80);
+			else
+				exp = gp_exp;
+			if (!exp) {
+				cur_ops->deferred_free(old_rp);
+			} else {
+				cur_ops->exp_sync();
+				list_add(&old_rp->rtort_free,
+					 &rcu_torture_removed);
+				list_for_each_entry_safe(rp, rp1,
+							 &rcu_torture_removed,
+							 rtort_free) {
+					i = rp->rtort_pipe_count;
+					if (i > RCU_TORTURE_PIPE_LEN)
+						i = RCU_TORTURE_PIPE_LEN;
+					atomic_inc(&rcu_torture_wcount[i]);
+					if (++rp->rtort_pipe_count >=
+					    RCU_TORTURE_PIPE_LEN) {
+						rp->rtort_mbtest = 0;
+						list_del(&rp->rtort_free);
+						rcu_torture_free(rp);
+					}
+				 }
+			}
 		}
 		rcutorture_record_progress(++rcu_torture_current_version);
-		oldbatch = cur_ops->completed();
 		rcu_stutter_wait("rcu_torture_writer");
 	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
 	VERBOSE_PRINTK_STRING("rcu_torture_writer task stopping");
···
 		schedule_timeout_uninterruptible(1 + rcu_random(&rand)%10);
 		udelay(rcu_random(&rand) & 0x3ff);
 		if (cur_ops->cb_barrier != NULL &&
-		    rcu_random(&rand) % (nfakewriters * 8) == 0)
+		    rcu_random(&rand) % (nfakewriters * 8) == 0) {
 			cur_ops->cb_barrier();
-		else
+		} else if (gp_normal == gp_exp) {
+			if (rcu_random(&rand) & 0x80)
+				cur_ops->sync();
+			else
+				cur_ops->exp_sync();
+		} else if (gp_normal) {
 			cur_ops->sync();
+		} else {
+			cur_ops->exp_sync();
+		}
 		rcu_stutter_wait("rcu_torture_fakewriter");
 	} while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP);
 
···
 					 torture_type, cpu);
 			starttime = jiffies;
 			n_online_attempts++;
-			if (cpu_up(cpu) == 0) {
+			ret = cpu_up(cpu);
+			if (ret) {
+				if (verbose)
+					pr_alert("%s" TORTURE_FLAG
+						 "rcu_torture_onoff task: online %d failed: errno %d\n",
+						 torture_type, cpu, ret);
+			} else {
 				if (verbose)
 					pr_alert("%s" TORTURE_FLAG
 						 "rcu_torture_onoff task: onlined %d\n",
···
 		rcu_torture_print_module_parms(cur_ops, "End of test: SUCCESS");
 }
 
+#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+static void rcu_torture_leak_cb(struct rcu_head *rhp)
+{
+}
+
+static void rcu_torture_err_cb(struct rcu_head *rhp)
+{
+	/*
+	 * This -might- happen due to race conditions, but is unlikely.
+	 * The scenario that leads to this happening is that the
+	 * first of the pair of duplicate callbacks is queued,
+	 * someone else starts a grace period that includes that
+	 * callback, then the second of the pair must wait for the
+	 * next grace period.  Unlikely, but can happen.  If it
+	 * does happen, the debug-objects subsystem won't have splatted.
+	 */
+	pr_alert("rcutorture: duplicated callback was invoked.\n");
+}
+#endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+
+/*
+ * Verify that double-free causes debug-objects to complain, but only
+ * if CONFIG_DEBUG_OBJECTS_RCU_HEAD=y.  Otherwise, say that the test
+ * cannot be carried out.
+ */
+static void rcu_test_debug_objects(void)
+{
+#ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+	struct rcu_head rh1;
+	struct rcu_head rh2;
+
+	init_rcu_head_on_stack(&rh1);
+	init_rcu_head_on_stack(&rh2);
+	pr_alert("rcutorture: WARN: Duplicate call_rcu() test starting.\n");
+
+	/* Try to queue the rh2 pair of callbacks for the same grace period. */
+	preempt_disable(); /* Prevent preemption from interrupting test. */
+	rcu_read_lock(); /* Make it impossible to finish a grace period. */
+	call_rcu(&rh1, rcu_torture_leak_cb); /* Start grace period. */
+	local_irq_disable(); /* Make it harder to start a new grace period. */
+	call_rcu(&rh2, rcu_torture_leak_cb);
+	call_rcu(&rh2, rcu_torture_err_cb); /* Duplicate callback. */
+	local_irq_enable();
+	rcu_read_unlock();
+	preempt_enable();
+
+	/* Wait for them all to get done so we can safely return. */
+	rcu_barrier();
+	pr_alert("rcutorture: WARN: Duplicate call_rcu() test complete.\n");
+	destroy_rcu_head_on_stack(&rh1);
+	destroy_rcu_head_on_stack(&rh2);
+#else /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+	pr_alert("rcutorture: !CONFIG_DEBUG_OBJECTS_RCU_HEAD, not testing duplicate call_rcu()\n");
+#endif /* #else #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */
+}
+
 static int __init
 rcu_torture_init(void)
 {
···
 	int cpu;
 	int firsterr = 0;
 	int retval;
-	static struct rcu_torture_ops *torture_ops[] =
-		{ &rcu_ops, &rcu_sync_ops, &rcu_expedited_ops,
-		  &rcu_bh_ops, &rcu_bh_sync_ops, &rcu_bh_expedited_ops,
-		  &srcu_ops, &srcu_sync_ops, &srcu_expedited_ops,
-		  &sched_ops, &sched_sync_ops, &sched_expedited_ops, };
+	static struct rcu_torture_ops *torture_ops[] = {
+		&rcu_ops, &rcu_bh_ops, &srcu_ops, &sched_ops,
+	};
 
 	mutex_lock(&fullstop_mutex);
 
···
 		firsterr = retval;
 		goto unwind;
 	}
+	if (object_debug)
+		rcu_test_debug_objects();
 	rcutorture_record_test_transition();
 	mutex_unlock(&fullstop_mutex);
 	return 0;

kernel/rcutree.c

···
 #include <linux/stop_machine.h>
 #include <linux/random.h>
 #include <linux/ftrace_event.h>
+#include <linux/suspend.h>
 
 #include "rcutree.h"
 #include <trace/events/rcu.h>
···
 DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 	.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
 	.dynticks = ATOMIC_INIT(1),
+#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
+	.dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE,
+	.dynticks_idle = ATOMIC_INIT(1),
+#endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
 };
 
 static long blimit = 10;	/* Maximum callbacks per rcu_do_batch. */
···
 
 static void rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
 				  struct rcu_data *rdp);
-static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *));
+static void force_qs_rnp(struct rcu_state *rsp,
+			 int (*f)(struct rcu_data *rsp, bool *isidle,
+				  unsigned long *maxj),
+			 bool *isidle, unsigned long *maxj);
 static void force_quiescent_state(struct rcu_state *rsp);
 static int rcu_pending(int cpu);
 
···
 
 	local_irq_save(flags);
 	rcu_eqs_enter(false);
+	rcu_sysidle_enter(&__get_cpu_var(rcu_dynticks), 0);
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(rcu_idle_enter);
···
 void rcu_user_enter(void)
 {
 	rcu_eqs_enter(1);
-}
-
-/**
- * rcu_user_enter_after_irq - inform RCU that we are going to resume userspace
- * after the current irq returns.
- *
- * This is similar to rcu_user_enter() but in the context of a non-nesting
- * irq. After this call, RCU enters into idle mode when the interrupt
- * returns.
- */
-void rcu_user_enter_after_irq(void)
-{
-	unsigned long flags;
-	struct rcu_dynticks *rdtp;
-
-	local_irq_save(flags);
-	rdtp = &__get_cpu_var(rcu_dynticks);
-	/* Ensure this irq is interrupting a non-idle RCU state.  */
-	WARN_ON_ONCE(!(rdtp->dynticks_nesting & DYNTICK_TASK_MASK));
-	rdtp->dynticks_nesting = 1;
-	local_irq_restore(flags);
 }
 #endif /* CONFIG_RCU_USER_QS */
 
···
 		trace_rcu_dyntick(TPS("--="), oldval, rdtp->dynticks_nesting);
 	else
 		rcu_eqs_enter_common(rdtp, oldval, true);
+	rcu_sysidle_enter(rdtp, 1);
 	local_irq_restore(flags);
 }
 
···
 
 	local_irq_save(flags);
 	rcu_eqs_exit(false);
+	rcu_sysidle_exit(&__get_cpu_var(rcu_dynticks), 0);
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(rcu_idle_exit);
···
 void rcu_user_exit(void)
 {
 	rcu_eqs_exit(1);
-}
-
-/**
- * rcu_user_exit_after_irq - inform RCU that we won't resume to userspace
- * idle mode after the current non-nesting irq returns.
- *
- * This is similar to rcu_user_exit() but in the context of an irq.
- * This is called when the irq has interrupted a userspace RCU idle mode
- * context. When the current non-nesting interrupt returns after this call,
- * the CPU won't restore the RCU idle mode.
- */
-void rcu_user_exit_after_irq(void)
-{
-	unsigned long flags;
-	struct rcu_dynticks *rdtp;
-
-	local_irq_save(flags);
-	rdtp = &__get_cpu_var(rcu_dynticks);
-	/* Ensure we are interrupting an RCU idle mode. */
-	WARN_ON_ONCE(rdtp->dynticks_nesting & DYNTICK_TASK_NEST_MASK);
-	rdtp->dynticks_nesting += DYNTICK_TASK_EXIT_IDLE;
-	local_irq_restore(flags);
 }
 #endif /* CONFIG_RCU_USER_QS */
 
···
 		trace_rcu_dyntick(TPS("++="), oldval, rdtp->dynticks_nesting);
 	else
 		rcu_eqs_exit_common(rdtp, oldval, true);
+	rcu_sysidle_exit(rdtp, 1);
 	local_irq_restore(flags);
 }
 
···
  * credit them with an implicit quiescent state.  Return 1 if this CPU
  * is in dynticks idle mode, which is an extended quiescent state.
  */
-static int dyntick_save_progress_counter(struct rcu_data *rdp)
+static int dyntick_save_progress_counter(struct rcu_data *rdp,
+					 bool *isidle, unsigned long *maxj)
 {
 	rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks);
+	rcu_sysidle_check_cpu(rdp, isidle, maxj);
 	return (rdp->dynticks_snap & 0x1) == 0;
 }
 
···
  * idle state since the last call to dyntick_save_progress_counter()
  * for this same CPU, or by virtue of having been offline.
  */
-static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
+static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
+				    bool *isidle, unsigned long *maxj)
 {
 	unsigned int curr;
 	unsigned int snap;
···
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
+	rcu_bind_gp_kthread();
 	raw_spin_lock_irq(&rnp->lock);
 	rsp->gp_flags = 0; /* Clear all flags: New grace period. */
 
···
 int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 {
 	int fqs_state = fqs_state_in;
+	bool isidle = false;
+	unsigned long maxj;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	rsp->n_force_qs++;
 	if (fqs_state == RCU_SAVE_DYNTICK) {
 		/* Collect dyntick-idle snapshots. */
-		force_qs_rnp(rsp, dyntick_save_progress_counter);
+		if (is_sysidle_rcu_state(rsp)) {
+			isidle = 1;
+			maxj = jiffies - ULONG_MAX / 4;
+		}
+		force_qs_rnp(rsp, dyntick_save_progress_counter,
+			     &isidle, &maxj);
+		rcu_sysidle_report_gp(rsp, isidle, maxj);
 		fqs_state = RCU_FORCE_QS;
 	} else {
 		/* Handle dyntick-idle and offline CPUs. */
-		force_qs_rnp(rsp, rcu_implicit_dynticks_qs);
+		isidle = 0;
+		force_qs_rnp(rsp, rcu_implicit_dynticks_qs, &isidle, &maxj);
 	}
 	/* Clear flag to prevent immediate re-entry. */
 	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
···
 
 	/*
 	 * We can't do wakeups while holding the rnp->lock, as that
-	 * could cause possible deadlocks with the rq->lock. Deter
-	 * the wakeup to interrupt context.
+	 * could cause possible deadlocks with the rq->lock. Defer
+	 * the wakeup to interrupt context.  And don't bother waking
+	 * up the running kthread.
 	 */
-	irq_work_queue(&rsp->wakeup_work);
+	if (current != rsp->gp_kthread)
+		irq_work_queue(&rsp->wakeup_work);
 }
 
 /*
···
  *
  * The caller must have suppressed start of new grace periods.
  */
-static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *))
+static void force_qs_rnp(struct rcu_state *rsp,
+			 int (*f)(struct rcu_data *rsp, bool *isidle,
+				  unsigned long *maxj),
+			 bool *isidle, unsigned long *maxj)
 {
 	unsigned long bit;
 	int cpu;
···
 		cpu = rnp->grplo;
 		bit = 1;
 		for (; cpu <= rnp->grphi; cpu++, bit <<= 1) {
-			if ((rnp->qsmask & bit) != 0 &&
-			    f(per_cpu_ptr(rsp->rda, cpu)))
-				mask |= bit;
+			if ((rnp->qsmask & bit) != 0) {
+				if ((rnp->qsmaskinit & bit) != 0)
+					*isidle = 0;
+				if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj))
+					mask |= bit;
+			}
 		}
 		if (mask != 0) {
 
···
 }
 
 /*
+ * RCU callback function to leak a callback.
+ */
+static void rcu_leak_callback(struct rcu_head *rhp)
+{
+}
+
+/*
  * Helper function for call_rcu() and friends.  The cpu argument will
  * normally be -1, indicating "currently running CPU".  It may specify
  * a CPU only if that CPU is a no-CBs CPU.  Currently, only _rcu_barrier()
···
 	struct rcu_data *rdp;
 
 	WARN_ON_ONCE((unsigned long)head & 0x3); /* Misaligned rcu_head! */
-	debug_rcu_head_queue(head);
+	if (debug_rcu_head_queue(head)) {
+		/* Probable double call_rcu(), so leak the callback. */
+		ACCESS_ONCE(head->func) = rcu_leak_callback;
+		WARN_ONCE(1, "__call_rcu(): Leaked duplicate callback\n");
+		return;
+	}
 	head->func = func;
 	head->next = NULL;
 
···
 	 * transition.  The "if" expression below therefore rounds the old
 	 * value up to the next even number and adds two before comparing.
 	 */
-	snap_done = ACCESS_ONCE(rsp->n_barrier_done);
+	snap_done = rsp->n_barrier_done;
 	_rcu_barrier_trace(rsp, "Check", -1, snap_done);
-	if (ULONG_CMP_GE(snap_done, ((snap + 1) & ~0x1) + 2)) {
+
+	/*
+	 * If the value in snap is odd, we needed to wait for the current
+	 * rcu_barrier() to complete, then wait for the next one, in other
+	 * words, we need the value of snap_done to be three larger than
+	 * the value of snap.  On the other hand, if the value in snap is
+	 * even, we only had to wait for the next rcu_barrier() to complete,
+	 * in other words, we need the value of snap_done to be only two
+	 * greater than the value of snap.  The "(snap + 3) & ~0x1" computes
+	 * this for us (thank you, Linus!).
+	 */
+	if (ULONG_CMP_GE(snap_done, (snap + 3) & ~0x1)) {
 		_rcu_barrier_trace(rsp, "EarlyExit", -1, snap_done);
 		smp_mb(); /* caller's subsequent code after above check. */
 		mutex_unlock(&rsp->barrier_mutex);
···
 	rdp->blimit = blimit;
 	init_callback_list(rdp);  /* Re-enable callbacks on this CPU. */
 	rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
+	rcu_sysidle_init_percpu_data(rdp->dynticks);
 	atomic_set(&rdp->dynticks->dynticks,
 		   (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1);
 	raw_spin_unlock(&rnp->lock);		/* irqs remain disabled. */
···
 		break;
 	}
 	trace_rcu_utilization(TPS("End CPU hotplug"));
+	return NOTIFY_OK;
+}
+
+static int rcu_pm_notify(struct notifier_block *self,
+			 unsigned long action, void *hcpu)
+{
+	switch (action) {
+	case PM_HIBERNATION_PREPARE:
+	case PM_SUSPEND_PREPARE:
+		if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */
+			rcu_expedited = 1;
+		break;
+	case PM_POST_HIBERNATION:
+	case PM_POST_SUSPEND:
+		rcu_expedited = 0;
+		break;
+	default:
+		break;
+	}
 	return NOTIFY_OK;
 }
 
···
 	 * or the scheduler are operational.
 	 */
 	cpu_notifier(rcu_cpu_notify, 0);
+	pm_notifier(rcu_pm_notify, 0);
 	for_each_online_cpu(cpu)
 		rcu_cpu_notify(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
 }

kernel/rcutree.h

···
 				    /* 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;
···
 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 */
 

kernel/rcutree_plugin.h

···
 #include <linux/gfp.h>
 #include <linux/oom.h>
 #include <linux/smpboot.h>
-#include <linux/tick.h>
+#include "time/tick-internal.h"
 
 #define RCU_KTHREAD_PRIO 1
 
···
 		smp_send_reschedule(cpu);
 #endif /* #ifdef CONFIG_NO_HZ_FULL */
 }
+
+
+#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
+
+/*
+ * Define RCU flavor that holds sysidle state.  This needs to be the
+ * most active flavor of RCU.
+ */
+#ifdef CONFIG_PREEMPT_RCU
+static struct rcu_state *rcu_sysidle_state = &rcu_preempt_state;
+#else /* #ifdef CONFIG_PREEMPT_RCU */
+static struct rcu_state *rcu_sysidle_state = &rcu_sched_state;
+#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
+
+static int full_sysidle_state;		/* Current system-idle state. */
+#define RCU_SYSIDLE_NOT		0	/* Some CPU is not idle. */
+#define RCU_SYSIDLE_SHORT	1	/* All CPUs idle for brief period. */
+#define RCU_SYSIDLE_LONG	2	/* All CPUs idle for long enough. */
+#define RCU_SYSIDLE_FULL	3	/* All CPUs idle, ready for sysidle. */
+#define RCU_SYSIDLE_FULL_NOTED	4	/* Actually entered sysidle state. */
+
+/*
+ * Invoked to note exit from irq or task transition to idle.  Note that
+ * usermode execution does -not- count as idle here!  After all, we want
+ * to detect full-system idle states, not RCU quiescent states and grace
+ * periods.  The caller must have disabled interrupts.
+ */
+static void rcu_sysidle_enter(struct rcu_dynticks *rdtp, int irq)
+{
+	unsigned long j;
+
+	/* Adjust nesting, check for fully idle. */
+	if (irq) {
+		rdtp->dynticks_idle_nesting--;
+		WARN_ON_ONCE(rdtp->dynticks_idle_nesting < 0);
+		if (rdtp->dynticks_idle_nesting != 0)
+			return;  /* Still not fully idle. */
+	} else {
+		if ((rdtp->dynticks_idle_nesting & DYNTICK_TASK_NEST_MASK) ==
+		    DYNTICK_TASK_NEST_VALUE) {
+			rdtp->dynticks_idle_nesting = 0;
+		} else {
+			rdtp->dynticks_idle_nesting -= DYNTICK_TASK_NEST_VALUE;
+			WARN_ON_ONCE(rdtp->dynticks_idle_nesting < 0);
+			return;  /* Still not fully idle. */
+		}
+	}
+
+	/* Record start of fully idle period. */
+	j = jiffies;
+	ACCESS_ONCE(rdtp->dynticks_idle_jiffies) = j;
+	smp_mb__before_atomic_inc();
+	atomic_inc(&rdtp->dynticks_idle);
+	smp_mb__after_atomic_inc();
+	WARN_ON_ONCE(atomic_read(&rdtp->dynticks_idle) & 0x1);
+}
+
+/*
+ * Unconditionally force exit from full system-idle state.  This is
+ * invoked when a normal CPU exits idle, but must be called separately
+ * for the timekeeping CPU (tick_do_timer_cpu).  The reason for this
+ * is that the timekeeping CPU is permitted to take scheduling-clock
+ * interrupts while the system is in system-idle state, and of course
+ * rcu_sysidle_exit() has no way of distinguishing a scheduling-clock
+ * interrupt from any other type of interrupt.
+ */
+void rcu_sysidle_force_exit(void)
+{
+	int oldstate = ACCESS_ONCE(full_sysidle_state);
+	int newoldstate;
+
+	/*
+	 * Each pass through the following loop attempts to exit full
+	 * system-idle state.  If contention proves to be a problem,
+	 * a trylock-based contention tree could be used here.
+	 */
+	while (oldstate > RCU_SYSIDLE_SHORT) {
+		newoldstate = cmpxchg(&full_sysidle_state,
+				      oldstate, RCU_SYSIDLE_NOT);
+		if (oldstate == newoldstate &&
+		    oldstate == RCU_SYSIDLE_FULL_NOTED) {
+			rcu_kick_nohz_cpu(tick_do_timer_cpu);
+			return; /* We cleared it, done! */
+		}
+		oldstate = newoldstate;
+	}
+	smp_mb(); /* Order initial oldstate fetch vs. later non-idle work. */
+}
+
+/*
+ * Invoked to note entry to irq or task transition from idle.  Note that
+ * usermode execution does -not- count as idle here!  The caller must
+ * have disabled interrupts.
+ */
+static void rcu_sysidle_exit(struct rcu_dynticks *rdtp, int irq)
+{
+	/* Adjust nesting, check for already non-idle. */
+	if (irq) {
+		rdtp->dynticks_idle_nesting++;
+		WARN_ON_ONCE(rdtp->dynticks_idle_nesting <= 0);
+		if (rdtp->dynticks_idle_nesting != 1)
+			return; /* Already non-idle. */
+	} else {
+		/*
+		 * Allow for irq misnesting.  Yes, it really is possible
+		 * to enter an irq handler then never leave it, and maybe
+		 * also vice versa.  Handle both possibilities.
+		 */
+		if (rdtp->dynticks_idle_nesting & DYNTICK_TASK_NEST_MASK) {
+			rdtp->dynticks_idle_nesting += DYNTICK_TASK_NEST_VALUE;
+			WARN_ON_ONCE(rdtp->dynticks_idle_nesting <= 0);
+			return; /* Already non-idle. */
+		} else {
+			rdtp->dynticks_idle_nesting = DYNTICK_TASK_EXIT_IDLE;
+		}
+	}
+
+	/* Record end of idle period. */
+	smp_mb__before_atomic_inc();
+	atomic_inc(&rdtp->dynticks_idle);
+	smp_mb__after_atomic_inc();
+	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks_idle) & 0x1));
+
+	/*
+	 * If we are the timekeeping CPU, we are permitted to be non-idle
+	 * during a system-idle state.  This must be the case, because
+	 * the timekeeping CPU has to take scheduling-clock interrupts
+	 * during the time that the system is transitioning to full
+	 * system-idle state.  This means that the timekeeping CPU must
+	 * invoke rcu_sysidle_force_exit() directly if it does anything
+	 * more than take a scheduling-clock interrupt.
+	 */
+	if (smp_processor_id() == tick_do_timer_cpu)
+		return;
+
+	/* Update system-idle state: We are clearly no longer fully idle! */
+	rcu_sysidle_force_exit();
+}
+
+/*
+ * Check to see if the current CPU is idle.  Note that usermode execution
+ * does not count as idle.  The caller must have disabled interrupts.
+ */
+static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle,
+				  unsigned long *maxj)
+{
+	int cur;
+	unsigned long j;
+	struct rcu_dynticks *rdtp = rdp->dynticks;
+
+	/*
+	 * If some other CPU has already reported non-idle, if this is
+	 * not the flavor of RCU that tracks sysidle state, or if this
+	 * is an offline or the timekeeping CPU, nothing to do.
+	 */
+	if (!*isidle || rdp->rsp != rcu_sysidle_state ||
+	    cpu_is_offline(rdp->cpu) || rdp->cpu == tick_do_timer_cpu)
+		return;
+	if (rcu_gp_in_progress(rdp->rsp))
+		WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu);
+
+	/* Pick up current idle and NMI-nesting counter and check. */
+	cur = atomic_read(&rdtp->dynticks_idle);
+	if (cur & 0x1) {
+		*isidle = false; /* We are not idle! */
+		return;
+	}
+	smp_mb(); /* Read counters before timestamps. */
+
+	/* Pick up timestamps. */
+	j = ACCESS_ONCE(rdtp->dynticks_idle_jiffies);
+	/* If this CPU entered idle more recently, update maxj timestamp. */
+	if (ULONG_CMP_LT(*maxj, j))
+		*maxj = j;
+}
+
+/*
+ * Is this the flavor of RCU that is handling full-system idle?
+ */
+static bool is_sysidle_rcu_state(struct rcu_state *rsp)
+{
+	return rsp == rcu_sysidle_state;
+}
+
+/*
+ * Bind the grace-period kthread for the sysidle flavor of RCU to the
+ * timekeeping CPU.
+ */
+static void rcu_bind_gp_kthread(void)
+{
+	int cpu = ACCESS_ONCE(tick_do_timer_cpu);
+
+	if (cpu < 0 || cpu >= nr_cpu_ids)
+		return;
+	if (raw_smp_processor_id() != cpu)
+		set_cpus_allowed_ptr(current, cpumask_of(cpu));
+}
+
+/*
+ * Return a delay in jiffies based on the number of CPUs, rcu_node
+ * leaf fanout, and jiffies tick rate.  The idea is to allow larger
+ * systems more time to transition to full-idle state in order to
+ * avoid the cache thrashing that otherwise occur on the state variable.
+ * Really small systems (less than a couple of tens of CPUs) should
+ * instead use a single global atomically incremented counter, and later
+ * versions of this will automatically reconfigure themselves accordingly.
+ */
+static unsigned long rcu_sysidle_delay(void)
+{
+	if (nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL)
+		return 0;
+	return DIV_ROUND_UP(nr_cpu_ids * HZ, rcu_fanout_leaf * 1000);
+}
+
+/*
+ * Advance the full-system-idle state.  This is invoked when all of
+ * the non-timekeeping CPUs are idle.
+ */
+static void rcu_sysidle(unsigned long j)
+{
+	/* Check the current state. */
+	switch (ACCESS_ONCE(full_sysidle_state)) {
+	case RCU_SYSIDLE_NOT:
+
+		/* First time all are idle, so note a short idle period. */
+		ACCESS_ONCE(full_sysidle_state) = RCU_SYSIDLE_SHORT;
+		break;
+
+	case RCU_SYSIDLE_SHORT:
+
+		/*
+		 * Idle for a bit, time to advance to next state?
+		 * cmpxchg failure means race with non-idle, let them win.
+		 */
+		if (ULONG_CMP_GE(jiffies, j + rcu_sysidle_delay()))
+			(void)cmpxchg(&full_sysidle_state,
+				      RCU_SYSIDLE_SHORT, RCU_SYSIDLE_LONG);
+		break;
+
+	case RCU_SYSIDLE_LONG:
+
+		/*
+		 * Do an additional check pass before advancing to full.
+		 * cmpxchg failure means race with non-idle, let them win.
+		 */
+		if (ULONG_CMP_GE(jiffies, j + rcu_sysidle_delay()))
+			(void)cmpxchg(&full_sysidle_state,
+				      RCU_SYSIDLE_LONG, RCU_SYSIDLE_FULL);
+		break;
+
+	default:
+		break;
+	}
+}
+
+/*
+ * Found a non-idle non-timekeeping CPU, so kick the system-idle state
+ * back to the beginning.
+ */
+static void rcu_sysidle_cancel(void)
+{
+	smp_mb();
+	ACCESS_ONCE(full_sysidle_state) = RCU_SYSIDLE_NOT;
+}
+
+/*
+ * Update the sysidle state based on the results of a force-quiescent-state
+ * scan of the CPUs' dyntick-idle state.
+ */
+static void rcu_sysidle_report(struct rcu_state *rsp, int isidle,
+			       unsigned long maxj, bool gpkt)
+{
+	if (rsp != rcu_sysidle_state)
+		return;  /* Wrong flavor, ignore. */
+	if (gpkt && nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL)
+		return;  /* Running state machine from timekeeping CPU. */
+	if (isidle)
+		rcu_sysidle(maxj);    /* More idle! */
+	else
+		rcu_sysidle_cancel(); /* Idle is over. */
+}
+
+/*
+ * Wrapper for rcu_sysidle_report() when called from the grace-period
+ * kthread's context.
+ */
+static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle,
+				  unsigned long maxj)
+{
+	rcu_sysidle_report(rsp, isidle, maxj, true);
+}
+
+/* Callback and function for forcing an RCU grace period. */
+struct rcu_sysidle_head {
+	struct rcu_head rh;
+	int inuse;
+};
+
+static void rcu_sysidle_cb(struct rcu_head *rhp)
+{
+	struct rcu_sysidle_head *rshp;
+
+	/*
+	 * The following memory barrier is needed to replace the
+	 * memory barriers that would normally be in the memory
+	 * allocator.
+	 */
+	smp_mb();  /* grace period precedes setting inuse. */
+
+	rshp = container_of(rhp, struct rcu_sysidle_head, rh);
+	ACCESS_ONCE(rshp->inuse) = 0;
+}
+
+/*
+ * Check to see if the system is fully idle, other than the timekeeping CPU.
+ * The caller must have disabled interrupts.
+ */
+bool rcu_sys_is_idle(void)
+{
+	static struct rcu_sysidle_head rsh;
+	int rss = ACCESS_ONCE(full_sysidle_state);
+
+	if (WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu))
+		return false;
+
+	/* Handle small-system case by doing a full scan of CPUs. */
+	if (nr_cpu_ids <= CONFIG_NO_HZ_FULL_SYSIDLE_SMALL) {
+		int oldrss = rss - 1;
+
+		/*
+		 * One pass to advance to each state up to _FULL.
+		 * Give up if any pass fails to advance the state.
+		 */
+		while (rss < RCU_SYSIDLE_FULL && oldrss < rss) {
+			int cpu;
+			bool isidle = true;
+			unsigned long maxj = jiffies - ULONG_MAX / 4;
+			struct rcu_data *rdp;
+
+			/* Scan all the CPUs looking for nonidle CPUs. */
+			for_each_possible_cpu(cpu) {
+				rdp = per_cpu_ptr(rcu_sysidle_state->rda, cpu);
+				rcu_sysidle_check_cpu(rdp, &isidle, &maxj);
+				if (!isidle)
+					break;
+			}
+			rcu_sysidle_report(rcu_sysidle_state,
+					   isidle, maxj, false);
+			oldrss = rss;
+			rss = ACCESS_ONCE(full_sysidle_state);
+		}
+	}
+
+	/* If this is the first observation of an idle period, record it. */
+	if (rss == RCU_SYSIDLE_FULL) {
+		rss = cmpxchg(&full_sysidle_state,
+			      RCU_SYSIDLE_FULL, RCU_SYSIDLE_FULL_NOTED);
+		return rss == RCU_SYSIDLE_FULL;
+	}
+
+	smp_mb(); /* ensure rss load happens before later caller actions. */
+
+	/* If already fully idle, tell the caller (in case of races). */
+	if (rss == RCU_SYSIDLE_FULL_NOTED)
+		return true;
+
+	/*
+	 * If we aren't there yet, and a grace period is not in flight,
+	 * initiate a grace period.  Either way, tell the caller that
+	 * we are not there yet.  We use an xchg() rather than an assignment
+	 * to make up for the memory barriers that would otherwise be
+	 * provided by the memory allocator.
+	 */
+	if (nr_cpu_ids > CONFIG_NO_HZ_FULL_SYSIDLE_SMALL &&
+	    !rcu_gp_in_progress(rcu_sysidle_state) &&
+	    !rsh.inuse && xchg(&rsh.inuse, 1) == 0)
+		call_rcu(&rsh.rh, rcu_sysidle_cb);
+	return false;
+}
+
+/*
+ * Initialize dynticks sysidle state for CPUs coming online.
+ */
+static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp)
+{
+	rdtp->dynticks_idle_nesting = DYNTICK_TASK_NEST_VALUE;
+}
+
+#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
+
+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)
+{
+	return false;
+}
+
+static void rcu_bind_gp_kthread(void)
+{
+}
+
+static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle,
+				  unsigned long maxj)
+{
+}
+
+static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp)
+{
+}
+
+#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */

kernel/time/Kconfig

···
 	 Note the boot CPU will still be kept outside the range to
 	 handle the timekeeping duty.
 
+config NO_HZ_FULL_SYSIDLE
+	bool "Detect full-system idle state for full dynticks system"
+	depends on NO_HZ_FULL
+	default n
+	help
+	 At least one CPU must keep the scheduling-clock tick running for
+	 timekeeping purposes whenever there is a non-idle CPU, where
+	 "non-idle" also includes dynticks CPUs as long as they are
+	 running non-idle tasks.  Because the underlying adaptive-tick
+	 support cannot distinguish between all CPUs being idle and
+	 all CPUs each running a single task in dynticks mode, the
+	 underlying support simply ensures that there is always a CPU
+	 handling the scheduling-clock tick, whether or not all CPUs
+	 are idle.  This Kconfig option enables scalable detection of
+	 the all-CPUs-idle state, thus allowing the scheduling-clock
+	 tick to be disabled when all CPUs are idle.  Note that scalable
+	 detection of the all-CPUs-idle state means that larger systems
+	 will be slower to declare the all-CPUs-idle state.
+
+	 Say Y if you would like to help debug all-CPUs-idle detection.
+
+	 Say N if you are unsure.
+
+config NO_HZ_FULL_SYSIDLE_SMALL
+	int "Number of CPUs above which large-system approach is used"
+	depends on NO_HZ_FULL_SYSIDLE
+	range 1 NR_CPUS
+	default 8
+	help
+	 The full-system idle detection mechanism takes a lazy approach
+	 on large systems, as is required to attain decent scalability.
+	 However, on smaller systems, scalability is not anywhere near as
+	 large a concern as is energy efficiency.  The sysidle subsystem
+	 therefore uses a fast but non-scalable algorithm for small
+	 systems and a lazier but scalable algorithm for large systems.
+	 This Kconfig parameter defines the number of CPUs in the largest
+	 system that will be considered to be "small".
+
+	 The default value will be fine in most cases.	Battery-powered
+	 systems that (1) enable NO_HZ_FULL_SYSIDLE, (2) have larger
+	 numbers of CPUs, and (3) are suffering from battery-lifetime
+	 problems due to long sysidle latencies might wish to experiment
+	 with larger values for this Kconfig parameter.  On the other
+	 hand, they might be even better served by disabling NO_HZ_FULL
+	 entirely, given that NO_HZ_FULL is intended for HPC and
+	 real-time workloads that at present do not tend to be run on
+	 battery-powered systems.
+
+	 Take the default if you are unsure.
+
 config NO_HZ
 	bool "Old Idle dynticks config"
 	depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS

lib/debugobjects.c

···
  * debug_object_activate - debug checks when an object is activated
  * @addr:	address of the object
  * @descr:	pointer to an object specific debug description structure
+ * Returns 0 for success, -EINVAL for check failed.
  */
-void debug_object_activate(void *addr, struct debug_obj_descr *descr)
+int debug_object_activate(void *addr, struct debug_obj_descr *descr)
 {
 	enum debug_obj_state state;
 	struct debug_bucket *db;
 	struct debug_obj *obj;
 	unsigned long flags;
+	int ret;
 	struct debug_obj o = { .object = addr,
 			       .state = ODEBUG_STATE_NOTAVAILABLE,
 			       .descr = descr };
 
 	if (!debug_objects_enabled)
-		return;
+		return 0;
 
 	db = get_bucket((unsigned long) addr);
 
···
 		case ODEBUG_STATE_INIT:
 		case ODEBUG_STATE_INACTIVE:
 			obj->state = ODEBUG_STATE_ACTIVE;
+			ret = 0;
 			break;
 
 		case ODEBUG_STATE_ACTIVE:
 			debug_print_object(obj, "activate");
 			state = obj->state;
 			raw_spin_unlock_irqrestore(&db->lock, flags);
-			debug_object_fixup(descr->fixup_activate, addr, state);
-			return;
+			ret = debug_object_fixup(descr->fixup_activate, addr, state);
+			return ret ? -EINVAL : 0;
 
 		case ODEBUG_STATE_DESTROYED:
 			debug_print_object(obj, "activate");
+			ret = -EINVAL;
 			break;
 		default:
+			ret = 0;
 			break;
 		}
 		raw_spin_unlock_irqrestore(&db->lock, flags);
-		return;
+		return ret;
 	}
 
 	raw_spin_unlock_irqrestore(&db->lock, flags);
···
 	 * true or not.
 	 */
 	if (debug_object_fixup(descr->fixup_activate, addr,
-			   ODEBUG_STATE_NOTAVAILABLE))
+			   ODEBUG_STATE_NOTAVAILABLE)) {
 		debug_print_object(&o, "activate");
+		return -EINVAL;
+	}
+	return 0;
 }
 
 /**