Merge remote-tracking branch 'rcu/rcu/next'

8 files changed, 215 insertions, 87 deletions

diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index e16c45b9ee77..4e8e14c34e42 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -4224,7 +4224,7 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s)
 	printk("\n%srcu_scheduler_active = %d, debug_locks = %d\n",
 	       !rcu_lockdep_current_cpu_online()
 			? "RCU used illegally from offline CPU!\n"
-			: rcu_is_cpu_idle()
+			: !rcu_is_watching()
 				? "RCU used illegally from idle CPU!\n"
 				: "",
 	       rcu_scheduler_active, debug_locks);
@@ -4247,7 +4247,7 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s)
 	 * So complain bitterly if someone does call rcu_read_lock(),
 	 * rcu_read_lock_bh() and so on from extended quiescent states.
 	 */
-	if (rcu_is_cpu_idle())
+	if (!rcu_is_watching())
 		printk("RCU used illegally from extended quiescent state!\n");
 
 	lockdep_print_held_locks(curr);
diff --git a/kernel/notifier.c b/kernel/notifier.c
index 2d5cc4ccff7f..1857c71bae40 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -51,7 +51,7 @@ static int notifier_chain_unregister(struct notifier_block **nl,
 {
 	while ((*nl) != NULL) {
 		if ((*nl) == n) {
-			rcu_assign_pointer(*nl, n->next);
+			rcu_assign_pointer(*nl, rcu_access_pointer(n->next));
 			return 0;
 		}
 		nl = &((*nl)->next);
diff --git a/kernel/rcu.h b/kernel/rcu.h
index 77131966c4ad..7859a0a3951e 100644
--- a/kernel/rcu.h
+++ b/kernel/rcu.h
@@ -122,4 +122,11 @@ int rcu_jiffies_till_stall_check(void);
 
 #endif /* #ifdef CONFIG_RCU_STALL_COMMON */
 
+/*
+ * 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)
+
 #endif /* __LINUX_RCU_H */
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index b02a339836b4..c07af1c4e1bb 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -148,7 +148,7 @@ int rcu_read_lock_bh_held(void)
 {
 	if (!debug_lockdep_rcu_enabled())
 		return 1;
-	if (rcu_is_cpu_idle())
+	if (!rcu_is_watching())
 		return 0;
 	if (!rcu_lockdep_current_cpu_online())
 		return 0;
@@ -298,7 +298,7 @@ EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read);
 #endif
 
 int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
-int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
+static int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
 
 module_param(rcu_cpu_stall_suppress, int, 0644);
 module_param(rcu_cpu_stall_timeout, int, 0644);
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 9ed6075dc562..312e9709713f 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -35,6 +35,7 @@
 #include <linux/time.h>
 #include <linux/cpu.h>
 #include <linux/prefetch.h>
+#include <linux/ftrace_event.h>
 
 #ifdef CONFIG_RCU_TRACE
 #include <trace/events/rcu.h>
@@ -58,16 +59,17 @@ static long long rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
 static void rcu_idle_enter_common(long long newval)
 {
 	if (newval) {
-		RCU_TRACE(trace_rcu_dyntick("--=",
+		RCU_TRACE(trace_rcu_dyntick(TPS("--="),
 					    rcu_dynticks_nesting, newval));
 		rcu_dynticks_nesting = newval;
 		return;
 	}
-	RCU_TRACE(trace_rcu_dyntick("Start", rcu_dynticks_nesting, newval));
+	RCU_TRACE(trace_rcu_dyntick(TPS("Start"),
+				    rcu_dynticks_nesting, newval));
 	if (!is_idle_task(current)) {
 		struct task_struct *idle = idle_task(smp_processor_id());
 
-		RCU_TRACE(trace_rcu_dyntick("Error on entry: not idle task",
+		RCU_TRACE(trace_rcu_dyntick(TPS("Entry error: not idle task"),
 					    rcu_dynticks_nesting, newval));
 		ftrace_dump(DUMP_ALL);
 		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
@@ -120,15 +122,15 @@ EXPORT_SYMBOL_GPL(rcu_irq_exit);
 static void rcu_idle_exit_common(long long oldval)
 {
 	if (oldval) {
-		RCU_TRACE(trace_rcu_dyntick("++=",
+		RCU_TRACE(trace_rcu_dyntick(TPS("++="),
 					    oldval, rcu_dynticks_nesting));
 		return;
 	}
-	RCU_TRACE(trace_rcu_dyntick("End", oldval, rcu_dynticks_nesting));
+	RCU_TRACE(trace_rcu_dyntick(TPS("End"), oldval, rcu_dynticks_nesting));
 	if (!is_idle_task(current)) {
 		struct task_struct *idle = idle_task(smp_processor_id());
 
-		RCU_TRACE(trace_rcu_dyntick("Error on exit: not idle task",
+		RCU_TRACE(trace_rcu_dyntick(TPS("Exit error: not idle task"),
 			  oldval, rcu_dynticks_nesting));
 		ftrace_dump(DUMP_ALL);
 		WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s",
@@ -174,18 +176,18 @@ void rcu_irq_enter(void)
 }
 EXPORT_SYMBOL_GPL(rcu_irq_enter);
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE)
 
 /*
  * Test whether RCU thinks that the current CPU is idle.
  */
-int rcu_is_cpu_idle(void)
+bool __rcu_is_watching(void)
 {
-	return !rcu_dynticks_nesting;
+	return rcu_dynticks_nesting;
 }
-EXPORT_SYMBOL(rcu_is_cpu_idle);
+EXPORT_SYMBOL(__rcu_is_watching);
 
-#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+#endif /* defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) */
 
 /*
  * Test whether the current CPU was interrupted from idle.  Nested
@@ -273,7 +275,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
 	if (&rcp->rcucblist == rcp->donetail) {
 		RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, 0, -1));
 		RCU_TRACE(trace_rcu_batch_end(rcp->name, 0,
-					      ACCESS_ONCE(rcp->rcucblist),
+					      !!ACCESS_ONCE(rcp->rcucblist),
 					      need_resched(),
 					      is_idle_task(current),
 					      false));
@@ -304,7 +306,8 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
 		RCU_TRACE(cb_count++);
 	}
 	RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count));
-	RCU_TRACE(trace_rcu_batch_end(rcp->name, cb_count, 0, need_resched(),
+	RCU_TRACE(trace_rcu_batch_end(rcp->name,
+				      cb_count, 0, need_resched(),
 				      is_idle_task(current),
 				      false));
 }
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 1dc9f3604ad8..aa127f74060c 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -61,13 +61,6 @@
 
 #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];
@@ -222,7 +215,7 @@ void rcu_note_context_switch(int cpu)
 }
 EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 
-DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
+static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 	.dynticks_nesting = DYNTICK_TASK_EXIT_IDLE,
 	.dynticks = ATOMIC_INIT(1),
 #ifdef CONFIG_NO_HZ_FULL_SYSIDLE
@@ -371,7 +364,8 @@ static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval,
 {
 	trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
 	if (!user && !is_idle_task(current)) {
-		struct task_struct *idle = idle_task(smp_processor_id());
+		struct task_struct *idle __maybe_unused =
+			idle_task(smp_processor_id());
 
 		trace_rcu_dyntick(TPS("Error on entry: not idle task"), oldval, 0);
 		ftrace_dump(DUMP_ORIG);
@@ -407,7 +401,7 @@ static void rcu_eqs_enter(bool user)
 	long long oldval;
 	struct rcu_dynticks *rdtp;
 
-	rdtp = &__get_cpu_var(rcu_dynticks);
+	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
 	if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE)
@@ -435,7 +429,7 @@ void rcu_idle_enter(void)
 
 	local_irq_save(flags);
 	rcu_eqs_enter(false);
-	rcu_sysidle_enter(&__get_cpu_var(rcu_dynticks), 0);
+	rcu_sysidle_enter(this_cpu_ptr(&rcu_dynticks), 0);
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(rcu_idle_enter);
@@ -478,7 +472,7 @@ void rcu_irq_exit(void)
 	struct rcu_dynticks *rdtp;
 
 	local_irq_save(flags);
-	rdtp = &__get_cpu_var(rcu_dynticks);
+	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	rdtp->dynticks_nesting--;
 	WARN_ON_ONCE(rdtp->dynticks_nesting < 0);
@@ -508,7 +502,8 @@ static void rcu_eqs_exit_common(struct rcu_dynticks *rdtp, long long oldval,
 	rcu_cleanup_after_idle(smp_processor_id());
 	trace_rcu_dyntick(TPS("End"), oldval, rdtp->dynticks_nesting);
 	if (!user && !is_idle_task(current)) {
-		struct task_struct *idle = idle_task(smp_processor_id());
+		struct task_struct *idle __maybe_unused =
+			idle_task(smp_processor_id());
 
 		trace_rcu_dyntick(TPS("Error on exit: not idle task"),
 				  oldval, rdtp->dynticks_nesting);
@@ -528,7 +523,7 @@ static void rcu_eqs_exit(bool user)
 	struct rcu_dynticks *rdtp;
 	long long oldval;
 
-	rdtp = &__get_cpu_var(rcu_dynticks);
+	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	WARN_ON_ONCE(oldval < 0);
 	if (oldval & DYNTICK_TASK_NEST_MASK)
@@ -555,7 +550,7 @@ void rcu_idle_exit(void)
 
 	local_irq_save(flags);
 	rcu_eqs_exit(false);
-	rcu_sysidle_exit(&__get_cpu_var(rcu_dynticks), 0);
+	rcu_sysidle_exit(this_cpu_ptr(&rcu_dynticks), 0);
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(rcu_idle_exit);
@@ -599,7 +594,7 @@ void rcu_irq_enter(void)
 	long long oldval;
 
 	local_irq_save(flags);
-	rdtp = &__get_cpu_var(rcu_dynticks);
+	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	rdtp->dynticks_nesting++;
 	WARN_ON_ONCE(rdtp->dynticks_nesting == 0);
@@ -620,7 +615,7 @@ void rcu_irq_enter(void)
  */
 void rcu_nmi_enter(void)
 {
-	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
 
 	if (rdtp->dynticks_nmi_nesting == 0 &&
 	    (atomic_read(&rdtp->dynticks) & 0x1))
@@ -642,7 +637,7 @@ void rcu_nmi_enter(void)
  */
 void rcu_nmi_exit(void)
 {
-	struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
 
 	if (rdtp->dynticks_nmi_nesting == 0 ||
 	    --rdtp->dynticks_nmi_nesting != 0)
@@ -655,21 +650,34 @@ void rcu_nmi_exit(void)
 }
 
 /**
- * rcu_is_cpu_idle - see if RCU thinks that the current CPU is idle
+ * __rcu_is_watching - are RCU read-side critical sections safe?
+ *
+ * Return true if RCU is watching the running CPU, which means that
+ * this CPU can safely enter RCU read-side critical sections.  Unlike
+ * rcu_is_watching(), the caller of __rcu_is_watching() must have at
+ * least disabled preemption.
+ */
+bool __rcu_is_watching(void)
+{
+	return atomic_read(this_cpu_ptr(&rcu_dynticks.dynticks)) & 0x1;
+}
+
+/**
+ * rcu_is_watching - see if RCU thinks that the current CPU is idle
  *
  * If the current CPU is in its idle loop and is neither in an interrupt
  * or NMI handler, return true.
  */
-int rcu_is_cpu_idle(void)
+bool rcu_is_watching(void)
 {
 	int ret;
 
 	preempt_disable();
-	ret = (atomic_read(&__get_cpu_var(rcu_dynticks).dynticks) & 0x1) == 0;
+	ret = __rcu_is_watching();
 	preempt_enable();
 	return ret;
 }
-EXPORT_SYMBOL(rcu_is_cpu_idle);
+EXPORT_SYMBOL_GPL(rcu_is_watching);
 
 #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)
 
@@ -703,7 +711,7 @@ bool rcu_lockdep_current_cpu_online(void)
 	if (in_nmi())
 		return 1;
 	preempt_disable();
-	rdp = &__get_cpu_var(rcu_sched_data);
+	rdp = this_cpu_ptr(&rcu_sched_data);
 	rnp = rdp->mynode;
 	ret = (rdp->grpmask & rnp->qsmaskinit) ||
 	      !rcu_scheduler_fully_active;
@@ -723,7 +731,7 @@ EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);
  */
 static int rcu_is_cpu_rrupt_from_idle(void)
 {
-	return __get_cpu_var(rcu_dynticks).dynticks_nesting <= 1;
+	return __this_cpu_read(rcu_dynticks.dynticks_nesting) <= 1;
 }
 
 /*
@@ -802,8 +810,11 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 
 static void record_gp_stall_check_time(struct rcu_state *rsp)
 {
-	rsp->gp_start = jiffies;
-	rsp->jiffies_stall = jiffies + rcu_jiffies_till_stall_check();
+	unsigned long j = ACCESS_ONCE(jiffies);
+
+	rsp->gp_start = j;
+	smp_wmb(); /* Record start time before stall time. */
+	rsp->jiffies_stall = j + rcu_jiffies_till_stall_check();
 }
 
 /*
@@ -945,17 +956,48 @@ static void print_cpu_stall(struct rcu_state *rsp)
 
 static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 {
+	unsigned long completed;
+	unsigned long gpnum;
+	unsigned long gps;
 	unsigned long j;
 	unsigned long js;
 	struct rcu_node *rnp;
 
-	if (rcu_cpu_stall_suppress)
+	if (rcu_cpu_stall_suppress || !rcu_gp_in_progress(rsp))
 		return;
 	j = ACCESS_ONCE(jiffies);
+
+	/*
+	 * Lots of memory barriers to reject false positives.
+	 *
+	 * The idea is to pick up rsp->gpnum, then rsp->jiffies_stall,
+	 * then rsp->gp_start, and finally rsp->completed.  These values
+	 * are updated in the opposite order with memory barriers (or
+	 * equivalent) during grace-period initialization and cleanup.
+	 * Now, a false positive can occur if we get an new value of
+	 * rsp->gp_start and a old value of rsp->jiffies_stall.  But given
+	 * the memory barriers, the only way that this can happen is if one
+	 * grace period ends and another starts between these two fetches.
+	 * Detect this by comparing rsp->completed with the previous fetch
+	 * from rsp->gpnum.
+	 *
+	 * Given this check, comparisons of jiffies, rsp->jiffies_stall,
+	 * and rsp->gp_start suffice to forestall false positives.
+	 */
+	gpnum = ACCESS_ONCE(rsp->gpnum);
+	smp_rmb(); /* Pick up ->gpnum first... */
 	js = ACCESS_ONCE(rsp->jiffies_stall);
+	smp_rmb(); /* ...then ->jiffies_stall before the rest... */
+	gps = ACCESS_ONCE(rsp->gp_start);
+	smp_rmb(); /* ...and finally ->gp_start before ->completed. */
+	completed = ACCESS_ONCE(rsp->completed);
+	if (ULONG_CMP_GE(completed, gpnum) ||
+	    ULONG_CMP_LT(j, js) ||
+	    ULONG_CMP_GE(gps, js))
+		return; /* No stall or GP completed since entering function. */
 	rnp = rdp->mynode;
 	if (rcu_gp_in_progress(rsp) &&
-	    (ACCESS_ONCE(rnp->qsmask) & rdp->grpmask) && ULONG_CMP_GE(j, js)) {
+	    (ACCESS_ONCE(rnp->qsmask) & rdp->grpmask)) {
 
 		/* We haven't checked in, so go dump stack. */
 		print_cpu_stall(rsp);
@@ -1310,7 +1352,7 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 }
 
 /*
- * Initialize a new grace period.
+ * Initialize a new grace period.  Return 0 if no grace period required.
  */
 static int rcu_gp_init(struct rcu_state *rsp)
 {
@@ -1319,18 +1361,27 @@ static int rcu_gp_init(struct rcu_state *rsp)
 
 	rcu_bind_gp_kthread();
 	raw_spin_lock_irq(&rnp->lock);
+	if (rsp->gp_flags == 0) {
+		/* Spurious wakeup, tell caller to go back to sleep.  */
+		raw_spin_unlock_irq(&rnp->lock);
+		return 0;
+	}
 	rsp->gp_flags = 0; /* Clear all flags: New grace period. */
 
-	if (rcu_gp_in_progress(rsp)) {
-		/* Grace period already in progress, don't start another.  */
+	if (WARN_ON_ONCE(rcu_gp_in_progress(rsp))) {
+		/*
+		 * Grace period already in progress, don't start another.
+		 * Not supposed to be able to happen.
+		 */
 		raw_spin_unlock_irq(&rnp->lock);
 		return 0;
 	}
 
 	/* Advance to a new grace period and initialize state. */
+	record_gp_stall_check_time(rsp);
+	smp_wmb(); /* Record GP times before starting GP. */
 	rsp->gpnum++;
 	trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start"));
-	record_gp_stall_check_time(rsp);
 	raw_spin_unlock_irq(&rnp->lock);
 
 	/* Exclude any concurrent CPU-hotplug operations. */
@@ -1379,7 +1430,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 /*
  * Do one round of quiescent-state forcing.
  */
-int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
+static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 {
 	int fqs_state = fqs_state_in;
 	bool isidle = false;
@@ -1464,8 +1515,12 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	rsp->fqs_state = RCU_GP_IDLE;
 	rdp = this_cpu_ptr(rsp->rda);
 	rcu_advance_cbs(rsp, rnp, rdp);  /* Reduce false positives below. */
-	if (cpu_needs_another_gp(rsp, rdp))
-		rsp->gp_flags = 1;
+	if (cpu_needs_another_gp(rsp, rdp)) {
+		rsp->gp_flags = RCU_GP_FLAG_INIT;
+		trace_rcu_grace_period(rsp->name,
+				       ACCESS_ONCE(rsp->gpnum),
+				       TPS("newreq"));
+	}
 	raw_spin_unlock_irq(&rnp->lock);
 }
 
@@ -1475,6 +1530,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 static int __noreturn rcu_gp_kthread(void *arg)
 {
 	int fqs_state;
+	int gf;
 	unsigned long j;
 	int ret;
 	struct rcu_state *rsp = arg;
@@ -1484,14 +1540,19 @@ static int __noreturn rcu_gp_kthread(void *arg)
 
 		/* Handle grace-period start. */
 		for (;;) {
+			trace_rcu_grace_period(rsp->name,
+					       ACCESS_ONCE(rsp->gpnum),
+					       TPS("reqwait"));
 			wait_event_interruptible(rsp->gp_wq,
-						 rsp->gp_flags &
+						 ACCESS_ONCE(rsp->gp_flags) &
 						 RCU_GP_FLAG_INIT);
-			if ((rsp->gp_flags & RCU_GP_FLAG_INIT) &&
-			    rcu_gp_init(rsp))
+			if (rcu_gp_init(rsp))
 				break;
 			cond_resched();
 			flush_signals(current);
+			trace_rcu_grace_period(rsp->name,
+					       ACCESS_ONCE(rsp->gpnum),
+					       TPS("reqwaitsig"));
 		}
 
 		/* Handle quiescent-state forcing. */
@@ -1501,10 +1562,16 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			j = HZ;
 			jiffies_till_first_fqs = HZ;
 		}
+		ret = 0;
 		for (;;) {
-			rsp->jiffies_force_qs = jiffies + j;
+			if (!ret)
+				rsp->jiffies_force_qs = jiffies + j;
+			trace_rcu_grace_period(rsp->name,
+					       ACCESS_ONCE(rsp->gpnum),
+					       TPS("fqswait"));
 			ret = wait_event_interruptible_timeout(rsp->gp_wq,
-					(rsp->gp_flags & RCU_GP_FLAG_FQS) ||
+					((gf = ACCESS_ONCE(rsp->gp_flags)) &
+					 RCU_GP_FLAG_FQS) ||
 					(!ACCESS_ONCE(rnp->qsmask) &&
 					 !rcu_preempt_blocked_readers_cgp(rnp)),
 					j);
@@ -1513,13 +1580,23 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			    !rcu_preempt_blocked_readers_cgp(rnp))
 				break;
 			/* If time for quiescent-state forcing, do it. */
-			if (ret == 0 || (rsp->gp_flags & RCU_GP_FLAG_FQS)) {
+			if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) ||
+			    (gf & RCU_GP_FLAG_FQS)) {
+				trace_rcu_grace_period(rsp->name,
+						       ACCESS_ONCE(rsp->gpnum),
+						       TPS("fqsstart"));
 				fqs_state = rcu_gp_fqs(rsp, fqs_state);
+				trace_rcu_grace_period(rsp->name,
+						       ACCESS_ONCE(rsp->gpnum),
+						       TPS("fqsend"));
 				cond_resched();
 			} else {
 				/* Deal with stray signal. */
 				cond_resched();
 				flush_signals(current);
+				trace_rcu_grace_period(rsp->name,
+						       ACCESS_ONCE(rsp->gpnum),
+						       TPS("fqswaitsig"));
 			}
 			j = jiffies_till_next_fqs;
 			if (j > HZ) {
@@ -1567,6 +1644,8 @@ rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
 		return;
 	}
 	rsp->gp_flags = RCU_GP_FLAG_INIT;
+	trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum),
+			       TPS("newreq"));
 
 	/*
 	 * We can't do wakeups while holding the rnp->lock, as that
@@ -2268,7 +2347,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 	 * If called from an extended quiescent state, invoke the RCU
 	 * core in order to force a re-evaluation of RCU's idleness.
 	 */
-	if (rcu_is_cpu_idle() && cpu_online(smp_processor_id()))
+	if (!rcu_is_watching() && cpu_online(smp_processor_id()))
 		invoke_rcu_core();
 
 	/* If interrupts were disabled or CPU offline, don't invoke RCU core. */
@@ -2738,10 +2817,13 @@ static int rcu_cpu_has_callbacks(int cpu, bool *all_lazy)
 
 	for_each_rcu_flavor(rsp) {
 		rdp = per_cpu_ptr(rsp->rda, cpu);
-		if (rdp->qlen != rdp->qlen_lazy)
+		if (!rdp->nxtlist)
+			continue;
+		hc = true;
+		if (rdp->qlen != rdp->qlen_lazy || !all_lazy) {
 			al = false;
-		if (rdp->nxtlist)
-			hc = true;
+			break;
+		}
 	}
 	if (all_lazy)
 		*all_lazy = al;
@@ -3308,8 +3390,8 @@ void __init rcu_init(void)
 
 	rcu_bootup_announce();
 	rcu_init_geometry();
-	rcu_init_one(&rcu_sched_state, &rcu_sched_data);
 	rcu_init_one(&rcu_bh_state, &rcu_bh_data);
+	rcu_init_one(&rcu_sched_state, &rcu_sched_data);
 	__rcu_init_preempt();
 	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 5f97eab602cd..52be957c9fe2 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -104,6 +104,8 @@ struct rcu_dynticks {
 				    /* idle-period nonlazy_posted snapshot. */
 	unsigned long last_accelerate;
 				    /* Last jiffy CBs were accelerated. */
+	unsigned long last_advance_all;
+				    /* Last jiffy CBs were all advanced. */
 	int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */
 #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
 };
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 130c97b027f2..8d85a5ce093a 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -96,10 +96,15 @@ static void __init rcu_bootup_announce_oddness(void)
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU_ZERO */
 #ifdef CONFIG_RCU_NOCB_CPU_ALL
 	pr_info("\tOffload RCU callbacks from all CPUs\n");
-	cpumask_setall(rcu_nocb_mask);
+	cpumask_copy(rcu_nocb_mask, cpu_possible_mask);
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU_ALL */
 #endif /* #ifndef CONFIG_RCU_NOCB_CPU_NONE */
 	if (have_rcu_nocb_mask) {
+		if (!cpumask_subset(rcu_nocb_mask, cpu_possible_mask)) {
+			pr_info("\tNote: kernel parameter 'rcu_nocbs=' contains nonexistent CPUs.\n");
+			cpumask_and(rcu_nocb_mask, cpu_possible_mask,
+				    rcu_nocb_mask);
+		}
 		cpulist_scnprintf(nocb_buf, sizeof(nocb_buf), rcu_nocb_mask);
 		pr_info("\tOffload RCU callbacks from CPUs: %s.\n", nocb_buf);
 		if (rcu_nocb_poll)
@@ -660,7 +665,7 @@ static void rcu_preempt_check_callbacks(int cpu)
 
 static void rcu_preempt_do_callbacks(void)
 {
-	rcu_do_batch(&rcu_preempt_state, &__get_cpu_var(rcu_preempt_data));
+	rcu_do_batch(&rcu_preempt_state, this_cpu_ptr(&rcu_preempt_data));
 }
 
 #endif /* #ifdef CONFIG_RCU_BOOST */
@@ -1332,7 +1337,7 @@ static void invoke_rcu_callbacks_kthread(void)
  */
 static bool rcu_is_callbacks_kthread(void)
 {
-	return __get_cpu_var(rcu_cpu_kthread_task) == current;
+	return __this_cpu_read(rcu_cpu_kthread_task) == current;
 }
 
 #define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000)
@@ -1382,8 +1387,8 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 
 static void rcu_kthread_do_work(void)
 {
-	rcu_do_batch(&rcu_sched_state, &__get_cpu_var(rcu_sched_data));
-	rcu_do_batch(&rcu_bh_state, &__get_cpu_var(rcu_bh_data));
+	rcu_do_batch(&rcu_sched_state, this_cpu_ptr(&rcu_sched_data));
+	rcu_do_batch(&rcu_bh_state, this_cpu_ptr(&rcu_bh_data));
 	rcu_preempt_do_callbacks();
 }
 
@@ -1402,7 +1407,7 @@ static void rcu_cpu_kthread_park(unsigned int cpu)
 
 static int rcu_cpu_kthread_should_run(unsigned int cpu)
 {
-	return __get_cpu_var(rcu_cpu_has_work);
+	return __this_cpu_read(rcu_cpu_has_work);
 }
 
 /*
@@ -1412,8 +1417,8 @@ static int rcu_cpu_kthread_should_run(unsigned int cpu)
  */
 static void rcu_cpu_kthread(unsigned int cpu)
 {
-	unsigned int *statusp = &__get_cpu_var(rcu_cpu_kthread_status);
-	char work, *workp = &__get_cpu_var(rcu_cpu_has_work);
+	unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status);
+	char work, *workp = this_cpu_ptr(&rcu_cpu_has_work);
 	int spincnt;
 
 	for (spincnt = 0; spincnt < 10; spincnt++) {
@@ -1630,17 +1635,23 @@ module_param(rcu_idle_lazy_gp_delay, int, 0644);
 extern int tick_nohz_enabled;
 
 /*
- * Try to advance callbacks for all flavors of RCU on the current CPU.
- * Afterwards, if there are any callbacks ready for immediate invocation,
- * return true.
+ * Try to advance callbacks for all flavors of RCU on the current CPU, but
+ * only if it has been awhile since the last time we did so.  Afterwards,
+ * if there are any callbacks ready for immediate invocation, return true.
  */
 static bool rcu_try_advance_all_cbs(void)
 {
 	bool cbs_ready = false;
 	struct rcu_data *rdp;
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
 	struct rcu_node *rnp;
 	struct rcu_state *rsp;
 
+	/* Exit early if we advanced recently. */
+	if (jiffies == rdtp->last_advance_all)
+		return 0;
+	rdtp->last_advance_all = jiffies;
+
 	for_each_rcu_flavor(rsp) {
 		rdp = this_cpu_ptr(rsp->rda);
 		rnp = rdp->mynode;
@@ -1739,6 +1750,8 @@ static void rcu_prepare_for_idle(int cpu)
 	 */
 	if (rdtp->all_lazy &&
 	    rdtp->nonlazy_posted != rdtp->nonlazy_posted_snap) {
+		rdtp->all_lazy = false;
+		rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted;
 		invoke_rcu_core();
 		return;
 	}
@@ -1768,17 +1781,11 @@ static void rcu_prepare_for_idle(int cpu)
  */
 static void rcu_cleanup_after_idle(int cpu)
 {
-	struct rcu_data *rdp;
-	struct rcu_state *rsp;
 
 	if (rcu_is_nocb_cpu(cpu))
 		return;
-	rcu_try_advance_all_cbs();
-	for_each_rcu_flavor(rsp) {
-		rdp = per_cpu_ptr(rsp->rda, cpu);
-		if (cpu_has_callbacks_ready_to_invoke(rdp))
-			invoke_rcu_core();
-	}
+	if (rcu_try_advance_all_cbs())
+		invoke_rcu_core();
 }
 
 /*
@@ -2108,15 +2115,22 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 
 	/* If we are not being polled and there is a kthread, awaken it ... */
 	t = ACCESS_ONCE(rdp->nocb_kthread);
-	if (rcu_nocb_poll | !t)
+	if (rcu_nocb_poll || !t) {
+		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+				    TPS("WakeNotPoll"));
 		return;
+	}
 	len = atomic_long_read(&rdp->nocb_q_count);
 	if (old_rhpp == &rdp->nocb_head) {
 		wake_up(&rdp->nocb_wq); /* ... only if queue was empty ... */
 		rdp->qlen_last_fqs_check = 0;
+		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeEmpty"));
 	} else if (len > rdp->qlen_last_fqs_check + qhimark) {
 		wake_up_process(t); /* ... or if many callbacks queued. */
 		rdp->qlen_last_fqs_check = LONG_MAX / 2;
+		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeOvf"));
+	} else {
+		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeNot"));
 	}
 	return;
 }
@@ -2140,10 +2154,12 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp,
 	if (__is_kfree_rcu_offset((unsigned long)rhp->func))
 		trace_rcu_kfree_callback(rdp->rsp->name, rhp,
 					 (unsigned long)rhp->func,
-					 rdp->qlen_lazy, rdp->qlen);
+					 -atomic_long_read(&rdp->nocb_q_count_lazy),
+					 -atomic_long_read(&rdp->nocb_q_count));
 	else
 		trace_rcu_callback(rdp->rsp->name, rhp,
-				   rdp->qlen_lazy, rdp->qlen);
+				   -atomic_long_read(&rdp->nocb_q_count_lazy),
+				   -atomic_long_read(&rdp->nocb_q_count));
 	return 1;
 }
 
@@ -2221,6 +2237,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 static int rcu_nocb_kthread(void *arg)
 {
 	int c, cl;
+	bool firsttime = 1;
 	struct rcu_head *list;
 	struct rcu_head *next;
 	struct rcu_head **tail;
@@ -2229,14 +2246,27 @@ static int rcu_nocb_kthread(void *arg)
 	/* Each pass through this loop invokes one batch of callbacks */
 	for (;;) {
 		/* If not polling, wait for next batch of callbacks. */
-		if (!rcu_nocb_poll)
+		if (!rcu_nocb_poll) {
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+					    TPS("Sleep"));
 			wait_event_interruptible(rdp->nocb_wq, rdp->nocb_head);
+		} else if (firsttime) {
+			firsttime = 0;
+			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+					    TPS("Poll"));
+		}
 		list = ACCESS_ONCE(rdp->nocb_head);
 		if (!list) {
+			if (!rcu_nocb_poll)
+				trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+						    TPS("WokeEmpty"));
 			schedule_timeout_interruptible(1);
 			flush_signals(current);
 			continue;
 		}
+		firsttime = 1;
+		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+				    TPS("WokeNonEmpty"));
 
 		/*
 		 * Extract queued callbacks, update counts, and wait
@@ -2257,7 +2287,11 @@ static int rcu_nocb_kthread(void *arg)
 			next = list->next;
 			/* Wait for enqueuing to complete, if needed. */
 			while (next == NULL && &list->next != tail) {
+				trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+						    TPS("WaitQueue"));
 				schedule_timeout_interruptible(1);
+				trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
+						    TPS("WokeQueue"));
 				next = list->next;
 			}
 			debug_rcu_head_unqueue(list);