Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RCU updates from Ingo Molnar:
 "Main RCU changes this cycle were:

   - 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.

   - Miscellaneous fixes.

   - Improved rcutorture test coverage.

   - Updated RCU documentation"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (30 commits)
  nohz_full: Force RCU's grace-period kthreads onto timekeeping CPU
  nohz_full: Add full-system-idle state machine
  jiffies: Avoid undefined behavior from signed overflow
  rcu: Simplify _rcu_barrier() processing
  rcu: Make rcutorture emit online failures if verbose
  rcu: Remove unused variable from rcu_torture_writer()
  rcu: Sort rcutorture module parameters
  rcu: Increase rcutorture test coverage
  rcu: Add duplicate-callback tests to rcutorture
  doc: Fix memory-barrier control-dependency example
  rcu: Update RTFP documentation
  nohz_full: Add full-system-idle arguments to API
  nohz_full: Add full-system idle states and variables
  nohz_full: Add per-CPU idle-state tracking
  nohz_full: Add rcu_dyntick data for scalable detection of all-idle state
  nohz_full: Add Kconfig parameter for scalable detection of all-idle state
  nohz_full: Add testing information to documentation
  rcu: Eliminate unused APIs intended for adaptive ticks
  rcu: Select IRQ_WORK from TREE_PREEMPT_RCU
  rculist: list_first_or_null_rcu() should use list_entry_rcu()
  ...

11 files changed, 873 insertions, 447 deletions

diff --git a/kernel/rcu.h b/kernel/rcu.h
index 7f8e7590e3e..77131966c4a 100644
--- a/kernel/rcu.h
+++ b/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;
 
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index cce6ba8bbac..33eb4620aa1 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -212,43 +212,6 @@ static inline void debug_rcu_head_free(struct rcu_head *head)
 }
 
 /*
- * 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)
@@ -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)
 {
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index aa344111de3..9ed6075dc56 100644
--- a/kernel/rcutiny.c
+++ b/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);
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
index 0cd385acccf..280d06cae35 100644
--- a/kernel/rcutiny_plugin.h
+++ b/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. */
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index f4871e52c54..be63101c617 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -52,72 +52,78 @@
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@freedesktop.org>");
 
-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) \
@@ -267,7 +273,7 @@ rcutorture_shutdown_notify(struct notifier_block *unused1,
  * Absorb kthreads into a kernel function that won't return, so that
  * they won't ever access module text or data again.
  */
-static void rcutorture_shutdown_absorb(char *title)
+static void rcutorture_shutdown_absorb(const char *title)
 {
 	if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
 		pr_notice(
@@ -337,7 +343,7 @@ rcu_random(struct rcu_random_state *rrsp)
 }
 
 static void
-rcu_stutter_wait(char *title)
+rcu_stutter_wait(const char *title)
 {
 	while (stutter_pause_test || !rcutorture_runnable) {
 		if (rcutorture_runnable)
@@ -360,13 +366,14 @@ struct rcu_torture_ops {
 	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);
 	int (*stats)(char *page);
 	int irq_capable;
 	int can_boost;
-	char *name;
+	const char *name;
 };
 
 static struct rcu_torture_ops *cur_ops;
@@ -443,81 +450,27 @@ static void rcu_torture_deferred_free(struct rcu_torture *p)
 	call_rcu(&p->rtort_rcu, rcu_torture_cb);
 }
 
-static struct rcu_torture_ops rcu_ops = {
-	.init		= NULL,
-	.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,
-	.call		= call_rcu,
-	.cb_barrier	= rcu_barrier,
-	.fqs		= rcu_force_quiescent_state,
-	.stats		= NULL,
-	.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 = {
+static struct rcu_torture_ops rcu_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,
+	.deferred_free	= rcu_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,
+	.exp_sync	= synchronize_rcu_expedited,
+	.call		= call_rcu,
+	.cb_barrier	= rcu_barrier,
 	.fqs		= rcu_force_quiescent_state,
 	.stats		= NULL,
 	.irq_capable	= 1,
 	.can_boost	= rcu_can_boost(),
-	.name		= "rcu_expedited"
+	.name		= "rcu"
 };
 
 /*
@@ -546,13 +499,14 @@ static void rcu_bh_torture_deferred_free(struct rcu_torture *p)
 }
 
 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,
@@ -561,38 +515,6 @@ static struct rcu_torture_ops rcu_bh_ops = {
 	.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"
-};
-
 /*
  * Definitions for srcu torture testing.
  */
@@ -667,6 +589,11 @@ static int srcu_torture_stats(char *page)
 	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,
@@ -675,45 +602,13 @@ static struct rcu_torture_ops srcu_ops = {
 	.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"
-};
-
 /*
  * Definitions for sched torture testing.
  */
@@ -742,6 +637,8 @@ static struct rcu_torture_ops sched_ops = {
 	.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,
@@ -749,35 +646,6 @@ static struct rcu_torture_ops sched_ops = {
 	.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"
-};
-
 /*
  * RCU torture priority-boost testing.  Runs one real-time thread per
  * CPU for moderate bursts, repeatedly registering RCU callbacks and
@@ -927,9 +795,10 @@ rcu_torture_fqs(void *arg)
 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);
 
@@ -954,10 +823,33 @@ rcu_torture_writer(void *arg)
 				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");
@@ -983,10 +875,18 @@ rcu_torture_fakewriter(void *arg)
 		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);
 
@@ -1364,7 +1264,7 @@ rcu_torture_stutter(void *arg)
 }
 
 static inline void
-rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, char *tag)
+rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 {
 	pr_alert("%s" TORTURE_FLAG
 		 "--- %s: nreaders=%d nfakewriters=%d "
@@ -1534,7 +1434,13 @@ rcu_torture_onoff(void *arg)
 					 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",
@@ -1934,6 +1840,62 @@ rcu_torture_cleanup(void)
 		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)
 {
@@ -1941,11 +1903,9 @@ 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);
 
@@ -2163,6 +2123,8 @@ rcu_torture_init(void)
 		firsterr = retval;
 		goto unwind;
 	}
+	if (object_debug)
+		rcu_test_debug_objects();
 	rcutorture_record_test_transition();
 	mutex_unlock(&fullstop_mutex);
 	return 0;
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 068de3a9360..32618b3fe4e 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -53,18 +53,38 @@
 #include <linux/delay.h>
 #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>
 
 #include "rcu.h"
 
+/*
+ * Strings used in tracepoints need to be exported via the
+ * tracing system such that tools like perf and trace-cmd can
+ * translate the string address pointers to actual text.
+ */
+#define TPS(x)	tracepoint_string(x)
+
 /* Data structures. */
 
 static struct lock_class_key rcu_node_class[RCU_NUM_LVLS];
 static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
 
-#define RCU_STATE_INITIALIZER(sname, sabbr, cr) { \
+/*
+ * In order to export the rcu_state name to the tracing tools, it
+ * needs to be added in the __tracepoint_string section.
+ * This requires defining a separate variable tp_<sname>_varname
+ * that points to the string being used, and this will allow
+ * the tracing userspace tools to be able to decipher the string
+ * address to the matching string.
+ */
+#define RCU_STATE_INITIALIZER(sname, sabbr, cr) \
+static char sname##_varname[] = #sname; \
+static const char *tp_##sname##_varname __used __tracepoint_string = sname##_varname; \
+struct rcu_state sname##_state = { \
 	.level = { &sname##_state.node[0] }, \
 	.call = cr, \
 	.fqs_state = RCU_GP_IDLE, \
@@ -75,16 +95,13 @@ static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
 	.orphan_donetail = &sname##_state.orphan_donelist, \
 	.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
 	.onoff_mutex = __MUTEX_INITIALIZER(sname##_state.onoff_mutex), \
-	.name = #sname, \
+	.name = sname##_varname, \
 	.abbr = sabbr, \
-}
-
-struct rcu_state rcu_sched_state =
-	RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
-DEFINE_PER_CPU(struct rcu_data, rcu_sched_data);
+}; \
+DEFINE_PER_CPU(struct rcu_data, sname##_data)
 
-struct rcu_state rcu_bh_state = RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh);
-DEFINE_PER_CPU(struct rcu_data, rcu_bh_data);
+RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
+RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh);
 
 static struct rcu_state *rcu_state;
 LIST_HEAD(rcu_struct_flavors);
@@ -178,7 +195,7 @@ void rcu_sched_qs(int cpu)
 	struct rcu_data *rdp = &per_cpu(rcu_sched_data, cpu);
 
 	if (rdp->passed_quiesce == 0)
-		trace_rcu_grace_period("rcu_sched", rdp->gpnum, "cpuqs");
+		trace_rcu_grace_period(TPS("rcu_sched"), rdp->gpnum, TPS("cpuqs"));
 	rdp->passed_quiesce = 1;
 }
 
@@ -187,7 +204,7 @@ void rcu_bh_qs(int cpu)
 	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
 
 	if (rdp->passed_quiesce == 0)
-		trace_rcu_grace_period("rcu_bh", rdp->gpnum, "cpuqs");
+		trace_rcu_grace_period(TPS("rcu_bh"), rdp->gpnum, TPS("cpuqs"));
 	rdp->passed_quiesce = 1;
 }
 
@@ -198,16 +215,20 @@ void rcu_bh_qs(int cpu)
  */
 void rcu_note_context_switch(int cpu)
 {
-	trace_rcu_utilization("Start context switch");
+	trace_rcu_utilization(TPS("Start context switch"));
 	rcu_sched_qs(cpu);
 	rcu_preempt_note_context_switch(cpu);
-	trace_rcu_utilization("End context switch");
+	trace_rcu_utilization(TPS("End context switch"));
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 
 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. */
@@ -226,7 +247,10 @@ module_param(jiffies_till_next_fqs, ulong, 0644);
 
 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);
 
@@ -345,11 +369,11 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
 static void rcu_e