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

Pull RCU changes from Paul E. McKenney:

  - Initialization/Kconfig updates: hide most Kconfig options from unsuspecting users.
    There's now a single high level configuration option:

      *
      * RCU Subsystem
      *
      Make expert-level adjustments to RCU configuration (RCU_EXPERT) [N/y/?] (NEW)

    Which if answered in the negative, leaves us with a single interactive
    configuration option:

      Offload RCU callback processing from boot-selected CPUs (RCU_NOCB_CPU) [N/y/?] (NEW)

    All the rest of the RCU options are configured automatically.

  - Remove all uses of RCU-protected array indexes: replace the
    rcu_[access|dereference]_index_check() APIs with READ_ONCE() and rcu_lockdep_assert().

  - RCU CPU-hotplug cleanups.

  - Updates to Tiny RCU: a race fix and further code shrinkage.

  - RCU torture-testing updates: fixes, speedups, cleanups and
    documentation updates.

  - Miscellaneous fixes.

  - Documentation updates.

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

13 files changed, 481 insertions, 380 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 94bbe46..9c9c9fa 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -398,7 +398,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
 		/* CPU didn't die: tell everyone.  Can't complain. */
-		smpboot_unpark_threads(cpu);
 		cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);
 		goto out_release;
 	}
@@ -463,6 +462,7 @@ static int smpboot_thread_call(struct notifier_block *nfb,
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 
+	case CPU_DOWN_FAILED:
 	case CPU_ONLINE:
 		smpboot_unpark_threads(cpu);
 		break;
@@ -479,7 +479,7 @@ static struct notifier_block smpboot_thread_notifier = {
 	.priority = CPU_PRI_SMPBOOT,
 };
 
-void __cpuinit smpboot_thread_init(void)
+void smpboot_thread_init(void)
 {
 	register_cpu_notifier(&smpboot_thread_notifier);
 }
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 232f00f..17fcb73 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -141,7 +141,7 @@ int perf_output_begin(struct perf_output_handle *handle,
 	perf_output_get_handle(handle);
 
 	do {
-		tail = ACCESS_ONCE(rb->user_page->data_tail);
+		tail = READ_ONCE_CTRL(rb->user_page->data_tail);
 		offset = head = local_read(&rb->head);
 		if (!rb->overwrite &&
 		    unlikely(CIRC_SPACE(head, tail, perf_data_size(rb)) < size))
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index ec8cce2..3224418 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -122,12 +122,12 @@ static int torture_lock_busted_write_lock(void)
 
 static void torture_lock_busted_write_delay(struct torture_random_state *trsp)
 {
-	const unsigned long longdelay_us = 100;
+	const unsigned long longdelay_ms = 100;
 
 	/* We want a long delay occasionally to force massive contention.  */
 	if (!(torture_random(trsp) %
-	      (cxt.nrealwriters_stress * 2000 * longdelay_us)))
-		mdelay(longdelay_us);
+	      (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
+		mdelay(longdelay_ms);
 #ifdef CONFIG_PREEMPT
 	if (!(torture_random(trsp) % (cxt.nrealwriters_stress * 20000)))
 		preempt_schedule();  /* Allow test to be preempted. */
@@ -160,14 +160,14 @@ static int torture_spin_lock_write_lock(void) __acquires(torture_spinlock)
 static void torture_spin_lock_write_delay(struct torture_random_state *trsp)
 {
 	const unsigned long shortdelay_us = 2;
-	const unsigned long longdelay_us = 100;
+	const unsigned long longdelay_ms = 100;
 
 	/* We want a short delay mostly to emulate likely code, and
 	 * we want a long delay occasionally to force massive contention.
 	 */
 	if (!(torture_random(trsp) %
-	      (cxt.nrealwriters_stress * 2000 * longdelay_us)))
-		mdelay(longdelay_us);
+	      (cxt.nrealwriters_stress * 2000 * longdelay_ms)))
+		mdelay(longdelay_ms);
 	if (!(torture_random(trsp) %
 	      (cxt.nrealwriters_stress * 2 * shortdelay_us)))
 		udelay(shortdelay_us);
@@ -309,7 +309,7 @@ static int torture_rwlock_read_lock_irq(void) __acquires(torture_rwlock)
 static void torture_rwlock_read_unlock_irq(void)
 __releases(torture_rwlock)
 {
-	write_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags);
+	read_unlock_irqrestore(&torture_rwlock, cxt.cur_ops->flags);
 }
 
 static struct lock_torture_ops rw_lock_irq_ops = {
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 8dbe276..59e3268 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -241,6 +241,7 @@ rcu_torture_free(struct rcu_torture *p)
 struct rcu_torture_ops {
 	int ttype;
 	void (*init)(void);
+	void (*cleanup)(void);
 	int (*readlock)(void);
 	void (*read_delay)(struct torture_random_state *rrsp);
 	void (*readunlock)(int idx);
@@ -477,10 +478,12 @@ static struct rcu_torture_ops rcu_busted_ops = {
  */
 
 DEFINE_STATIC_SRCU(srcu_ctl);
+static struct srcu_struct srcu_ctld;
+static struct srcu_struct *srcu_ctlp = &srcu_ctl;
 
-static int srcu_torture_read_lock(void) __acquires(&srcu_ctl)
+static int srcu_torture_read_lock(void) __acquires(srcu_ctlp)
 {
-	return srcu_read_lock(&srcu_ctl);
+	return srcu_read_lock(srcu_ctlp);
 }
 
 static void srcu_read_delay(struct torture_random_state *rrsp)
@@ -499,49 +502,49 @@ static void srcu_read_delay(struct torture_random_state *rrsp)
 		rcu_read_delay(rrsp);
 }
 
-static void srcu_torture_read_unlock(int idx) __releases(&srcu_ctl)
+static void srcu_torture_read_unlock(int idx) __releases(srcu_ctlp)
 {
-	srcu_read_unlock(&srcu_ctl, idx);
+	srcu_read_unlock(srcu_ctlp, idx);
 }
 
 static unsigned long srcu_torture_completed(void)
 {
-	return srcu_batches_completed(&srcu_ctl);
+	return srcu_batches_completed(srcu_ctlp);
 }
 
 static void srcu_torture_deferred_free(struct rcu_torture *rp)
 {
-	call_srcu(&srcu_ctl, &rp->rtort_rcu, rcu_torture_cb);
+	call_srcu(srcu_ctlp, &rp->rtort_rcu, rcu_torture_cb);
 }
 
 static void srcu_torture_synchronize(void)
 {
-	synchronize_srcu(&srcu_ctl);
+	synchronize_srcu(srcu_ctlp);
 }
 
 static void srcu_torture_call(struct rcu_head *head,
 			      void (*func)(struct rcu_head *head))
 {
-	call_srcu(&srcu_ctl, head, func);
+	call_srcu(srcu_ctlp, head, func);
 }
 
 static void srcu_torture_barrier(void)
 {
-	srcu_barrier(&srcu_ctl);
+	srcu_barrier(srcu_ctlp);
 }
 
 static void srcu_torture_stats(void)
 {
 	int cpu;
-	int idx = srcu_ctl.completed & 0x1;
+	int idx = srcu_ctlp->completed & 0x1;
 
 	pr_alert("%s%s per-CPU(idx=%d):",
 		 torture_type, TORTURE_FLAG, idx);
 	for_each_possible_cpu(cpu) {
 		long c0, c1;
 
-		c0 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx];
-		c1 = (long)per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx];
+		c0 = (long)per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu)->c[!idx];
+		c1 = (long)per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu)->c[idx];
 		pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
 	}
 	pr_cont("\n");
@@ -549,7 +552,7 @@ static void srcu_torture_stats(void)
 
 static void srcu_torture_synchronize_expedited(void)
 {
-	synchronize_srcu_expedited(&srcu_ctl);
+	synchronize_srcu_expedited(srcu_ctlp);
 }
 
 static struct rcu_torture_ops srcu_ops = {
@@ -569,6 +572,38 @@ static struct rcu_torture_ops srcu_ops = {
 	.name		= "srcu"
 };
 
+static void srcu_torture_init(void)
+{
+	rcu_sync_torture_init();
+	WARN_ON(init_srcu_struct(&srcu_ctld));
+	srcu_ctlp = &srcu_ctld;
+}
+
+static void srcu_torture_cleanup(void)
+{
+	cleanup_srcu_struct(&srcu_ctld);
+	srcu_ctlp = &srcu_ctl; /* In case of a later rcutorture run. */
+}
+
+/* As above, but dynamically allocated. */
+static struct rcu_torture_ops srcud_ops = {
+	.ttype		= SRCU_FLAVOR,
+	.init		= srcu_torture_init,
+	.cleanup	= srcu_torture_cleanup,
+	.readlock	= srcu_torture_read_lock,
+	.read_delay	= srcu_read_delay,
+	.readunlock	= srcu_torture_read_unlock,
+	.started	= NULL,
+	.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		= "srcud"
+};
+
 /*
  * Definitions for sched torture testing.
  */
@@ -672,8 +707,8 @@ static void rcu_torture_boost_cb(struct rcu_head *head)
 	struct rcu_boost_inflight *rbip =
 		container_of(head, struct rcu_boost_inflight, rcu);
 
-	smp_mb(); /* Ensure RCU-core accesses precede clearing ->inflight */
-	rbip->inflight = 0;
+	/* Ensure RCU-core accesses precede clearing ->inflight */
+	smp_store_release(&rbip->inflight, 0);
 }
 
 static int rcu_torture_boost(void *arg)
@@ -710,9 +745,9 @@ static int rcu_torture_boost(void *arg)
 		call_rcu_time = jiffies;
 		while (ULONG_CMP_LT(jiffies, endtime)) {
 			/* If we don't have a callback in flight, post one. */
-			if (!rbi.inflight) {
-				smp_mb(); /* RCU core before ->inflight = 1. */
-				rbi.inflight = 1;
+			if (!smp_load_acquire(&rbi.inflight)) {
+				/* RCU core before ->inflight = 1. */
+				smp_store_release(&rbi.inflight, 1);
 				call_rcu(&rbi.rcu, rcu_torture_boost_cb);
 				if (jiffies - call_rcu_time >
 					 test_boost_duration * HZ - HZ / 2) {
@@ -751,11 +786,10 @@ checkwait:	stutter_wait("rcu_torture_boost");
 	} while (!torture_must_stop());
 
 	/* Clean up and exit. */
-	while (!kthread_should_stop() || rbi.inflight) {
+	while (!kthread_should_stop() || smp_load_acquire(&rbi.inflight)) {
 		torture_shutdown_absorb("rcu_torture_boost");
 		schedule_timeout_uninterruptible(1);
 	}
-	smp_mb(); /* order accesses to ->inflight before stack-frame death. */
 	destroy_rcu_head_on_stack(&rbi.rcu);
 	torture_kthread_stopping("rcu_torture_boost");
 	return 0;
@@ -1054,7 +1088,7 @@ static void rcu_torture_timer(unsigned long unused)
 	p = rcu_dereference_check(rcu_torture_current,
 				  rcu_read_lock_bh_held() ||
 				  rcu_read_lock_sched_held() ||
-				  srcu_read_lock_held(&srcu_ctl));
+				  srcu_read_lock_held(srcu_ctlp));
 	if (p == NULL) {
 		/* Leave because rcu_torture_writer is not yet underway */
 		cur_ops->readunlock(idx);
@@ -1128,7 +1162,7 @@ rcu_torture_reader(void *arg)
 		p = rcu_dereference_check(rcu_torture_current,
 					  rcu_read_lock_bh_held() ||
 					  rcu_read_lock_sched_held() ||
-					  srcu_read_lock_held(&srcu_ctl));
+					  srcu_read_lock_held(srcu_ctlp));
 		if (p == NULL) {
 			/* Wait for rcu_torture_writer to get underway */
 			cur_ops->readunlock(idx);
@@ -1413,12 +1447,15 @@ static int rcu_torture_barrier_cbs(void *arg)
 	do {
 		wait_event(barrier_cbs_wq[myid],
 			   (newphase =
-			    ACCESS_ONCE(barrier_phase)) != lastphase ||
+			    smp_load_acquire(&barrier_phase)) != lastphase ||
 			   torture_must_stop());
 		lastphase = newphase;
-		smp_mb(); /* ensure barrier_phase load before ->call(). */
 		if (torture_must_stop())
 			break;
+		/*
+		 * The above smp_load_acquire() ensures barrier_phase load
+		 * is ordered before the folloiwng ->call().
+		 */
 		cur_ops->call(&rcu, rcu_torture_barrier_cbf);
 		if (atomic_dec_and_test(&barrier_cbs_count))
 			wake_up(&barrier_wq);
@@ -1439,8 +1476,8 @@ static int rcu_torture_barrier(void *arg)
 	do {
 		atomic_set(&barrier_cbs_invoked, 0);
 		atomic_set(&barrier_cbs_count, n_barrier_cbs);
-		smp_mb(); /* Ensure barrier_phase after prior assignments. */
-		barrier_phase = !barrier_phase;
+		/* Ensure barrier_phase ordered after prior assignments. */
+		smp_store_release(&barrier_phase, !barrier_phase);
 		for (i = 0; i < n_barrier_cbs; i++)
 			wake_up(&barrier_cbs_wq[i]);
 		wait_event(barrier_wq,
@@ -1588,10 +1625,14 @@ rcu_torture_cleanup(void)
 			rcutorture_booster_cleanup(i);
 	}
 
-	/* Wait for all RCU callbacks to fire.  */
-
+	/*
+	 * Wait for all RCU callbacks to fire, then do flavor-specific
+	 * cleanup operations.
+	 */
 	if (cur_ops->cb_barrier != NULL)
 		cur_ops->cb_barrier();
+	if (cur_ops->cleanup != NULL)
+		cur_ops->cleanup();
 
 	rcu_torture_stats_print();  /* -After- the stats thread is stopped! */
 
@@ -1668,8 +1709,8 @@ rcu_torture_init(void)
 	int cpu;
 	int firsterr = 0;
 	static struct rcu_torture_ops *torture_ops[] = {
-		&rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &sched_ops,
-		RCUTORTURE_TASKS_OPS
+		&rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops,
+		&sched_ops, RCUTORTURE_TASKS_OPS
 	};
 
 	if (!torture_init_begin(torture_type, verbose, &torture_runnable))
@@ -1701,7 +1742,7 @@ rcu_torture_init(void)
 	if (nreaders >= 0) {
 		nrealreaders = nreaders;
 	} else {
-		nrealreaders = num_online_cpus() - 1;
+		nrealreaders = num_online_cpus() - 2 - nreaders;
 		if (nrealreaders <= 0)
 			nrealreaders = 1;
 	}
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index cad76e7..fb33d35 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -151,7 +151,7 @@ static unsigned long srcu_readers_seq_idx(struct srcu_struct *sp, int idx)
 	unsigned long t;
 
 	for_each_possible_cpu(cpu) {
-		t = ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->seq[idx]);
+		t = READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->seq[idx]);
 		sum += t;
 	}
 	return sum;
@@ -168,7 +168,7 @@ static unsigned long srcu_readers_active_idx(struct srcu_struct *sp, int idx)
 	unsigned long t;
 
 	for_each_possible_cpu(cpu) {
-		t = ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]);
+		t = READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]);
 		sum += t;
 	}
 	return sum;
@@ -265,8 +265,8 @@ static int srcu_readers_active(struct srcu_struct *sp)
 	unsigned long sum = 0;
 
 	for_each_possible_cpu(cpu) {
-		sum += ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[0]);
-		sum += ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[1]);
+		sum += READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[0]);
+		sum += READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[1]);
 	}
 	return sum;
 }
@@ -296,7 +296,7 @@ int __srcu_read_lock(struct srcu_struct *sp)
 {
 	int idx;
 
-	idx = ACCESS_ONCE(sp->completed) & 0x1;
+	idx = READ_ONCE(sp->completed) & 0x1;
 	preempt_disable();
 	__this_cpu_inc(sp->per_cpu_ref->c[idx]);
 	smp_mb(); /* B */  /* Avoid leaking the critical section. */
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 069742d..591af0c 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -49,39 +49,6 @@ static void __call_rcu(struct rcu_head *head,
 
 #include "tiny_plugin.h"
 
-/*
- * Enter idle, which is an extended quiescent state if we have fully
- * entered that mode.
- */
-void rcu_idle_enter(void)
-{
-}
-EXPORT_SYMBOL_GPL(rcu_idle_enter);
-
-/*
- * Exit an interrupt handler towards idle.
- */
-void rcu_irq_exit(void)
-{
-}
-EXPORT_SYMBOL_GPL(rcu_irq_exit);
-
-/*
- * Exit idle, so that we are no longer in an extended quiescent state.
- */
-void rcu_idle_exit(void)
-{
-}
-EXPORT_SYMBOL_GPL(rcu_idle_exit);
-
-/*
- * Enter an interrupt handler, moving away from idle.
- */
-void rcu_irq_enter(void)
-{
-}
-EXPORT_SYMBOL_GPL(rcu_irq_enter);
-
 #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE)
 
 /*
@@ -170,6 +137,11 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
 
 	/* Move the ready-to-invoke callbacks to a local list. */
 	local_irq_save(flags);
+	if (rcp->donetail == &rcp->rcucblist) {
+		/* No callbacks ready, so just leave. */
+		local_irq_restore(flags);
+		return;
+	}
 	RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, rcp->qlen, -1));
 	list = rcp->rcucblist;
 	rcp->rcucblist = *rcp->donetail;
diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h
index f94e209..e492a52 100644
--- a/kernel/rcu/tiny_plugin.h
+++ b/kernel/rcu/tiny_plugin.h
@@ -144,16 +144,17 @@ static void check_cpu_stall(struct rcu_ctrlblk *rcp)
 		return;
 	rcp->ticks_this_gp++;
 	j = jiffies;
-	js = ACCESS_ONCE(rcp->jiffies_stall);
+	js = READ_ONCE(rcp->jiffies_stall);
 	if (rcp->rcucblist && ULONG_CMP_GE(j, js)) {
 		pr_err("INFO: %s stall on CPU (%lu ticks this GP) idle=%llx (t=%lu jiffies q=%ld)\n",
 		       rcp->name, rcp->ticks_this_gp, DYNTICK_TASK_EXIT_IDLE,
 		       jiffies - rcp->gp_start, rcp->qlen);
 		dump_stack();
-		ACCESS_ONCE(rcp->jiffies_stall) = jiffies +
-			3 * rcu_jiffies_till_stall_check() + 3;
+		WRITE_ONCE(rcp->jiffies_stall,
+			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
 	} else if (ULONG_CMP_GE(j, js)) {
-		ACCESS_ONCE(rcp->jiffies_stall) = jiffies + rcu_jiffies_till_stall_check();
+		WRITE_ONCE(rcp->jiffies_stall,
+			   jiffies + rcu_jiffies_till_stall_check());
 	}
 }
 
@@ -161,7 +162,8 @@ static void reset_cpu_stall_ticks(struct rcu_ctrlblk *rcp)
 {
 	rcp->ticks_this_gp = 0;
 	rcp->gp_start = jiffies;
-	ACCESS_ONCE(rcp->jiffies_stall) = jiffies + rcu_jiffies_till_stall_check();
+	WRITE_ONCE(rcp->jiffies_stall,
+		   jiffies + rcu_jiffies_till_stall_check());
 }
 
 static void check_cpu_stalls(void)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 8cf7304..add0429 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -91,7 +91,7 @@ static const char *tp_##sname##_varname __used __tracepoint_string = sname##_var
 
 #define RCU_STATE_INITIALIZER(sname, sabbr, cr) \
 DEFINE_RCU_TPS(sname) \
-DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data); \
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data); \
 struct rcu_state sname##_state = { \
 	.level = { &sname##_state.node[0] }, \
 	.rda = &sname##_data, \
@@ -110,11 +110,18 @@ struct rcu_state sname##_state = { \
 RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
 RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh);
 
-static struct rcu_state *rcu_state_p;
+static struct rcu_state *const rcu_state_p;
+static struct rcu_data __percpu *const rcu_data_p;
 LIST_HEAD(rcu_struct_flavors);
 
-/* Increase (but not decrease) the CONFIG_RCU_FANOUT_LEAF at boot time. */
-static int rcu_fanout_leaf = CONFIG_RCU_FANOUT_LEAF;
+/* Dump rcu_node combining tree at boot to verify correct setup. */
+static bool dump_tree;
+module_param(dump_tree, bool, 0444);
+/* Control rcu_node-tree auto-balancing at boot time. */
+static bool rcu_fanout_exact;
+module_param(rcu_fanout_exact, bool, 0444);
+/* Increase (but not decrease) the RCU_FANOUT_LEAF at boot time. */
+static int rcu_fanout_leaf = RCU_FANOUT_LEAF;
 module_param(rcu_fanout_leaf, int, 0444);
 int rcu_num_lvls __read_mostly = RCU_NUM_LVLS;
 static int num_rcu_lvl[] = {  /* Number of rcu_nodes at specified level. */
@@ -159,17 +166,46 @@ static void invoke_rcu_core(void);
 static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
 
 /* rcuc/rcub kthread realtime priority */
+#ifdef CONFIG_RCU_KTHREAD_PRIO
 static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO;
+#else /* #ifdef CONFIG_RCU_KTHREAD_PRIO */
+static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0;
+#endif /* #else #ifdef CONFIG_RCU_KTHREAD_PRIO */
 module_param(kthread_prio, int, 0644);
 
 /* Delay in jiffies for grace-period initialization delays, debug only. */
+
+#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT
+static int gp_preinit_delay = CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT_DELAY;
+module_param(gp_preinit_delay, int, 0644);
+#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT */
+static const int gp_preinit_delay;
+#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT */
+
 #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT
 static int gp_init_delay = CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY;
 module_param(gp_init_delay, int, 0644);
 #else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */
 static const int gp_init_delay;
 #endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */
-#define PER_RCU_NODE_PERIOD 10	/* Number of grace periods between delays. */
+
+#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP
+static int gp_cleanup_delay = CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY;
+module_param(gp_cleanup_delay, int, 0644);
+#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP */
+static const int gp_cleanup_delay;
+#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP */
+
+/*
+ * Number of grace periods between delays, normalized by the duration of
+ * the delay.  The longer the the delay, the more the grace periods between
+ * each delay.  The reason for this normalization is that it means that,
+ * for non-zero delays, the overall slowdown of grace periods is constant
+ * regardless of the duration of the delay.  This arrangement balances
+ * the need for long delays to increase some race probabilities with the
+ * need for fast grace periods to increase other race probabilities.
+ */
+#define PER_RCU_NODE_PERIOD 3	/* Number of grace periods between delays. */
 
 /*
  * Track the rcutorture test sequence number and the update version
@@ -191,17 +227,17 @@ unsigned long rcutorture_vernum;
  */
 unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
 {
-	return ACCESS_ONCE(rnp->qsmaskinitnext);
+	return READ_ONCE(rnp->qsmaskinitnext);
 }
 
 /*
- * Return true if an RCU grace period is in progress.  The ACCESS_ONCE()s
+ * Return true if an RCU grace period is in progress.  The READ_ONCE()s
  * permit this function to be invoked without holding the root rcu_node
  * structure's ->lock, but of course results can be subject to change.
  */
 static int rcu_gp_in_progress(struct rcu_state *rsp)
 {
-	return ACCESS_ONCE(rsp->completed) != ACCESS_ONCE(rsp->gpnum);
+	return READ_ONCE(rsp->completed) != READ_ONCE(rsp->gpnum);
 }
 
 /*
@@ -278,8 +314,8 @@ static void rcu_momentary_dyntick_idle(void)
 		if (!(resched_mask & rsp->flavor_mask))
 			continue;
 		smp_mb(); /* rcu_sched_qs_mask before cond_resched_completed. */
-		if (ACCESS_ONCE(rdp->mynode->completed) !=
-		    ACCESS_ONCE(rdp->cond_resched_completed))
+		if (READ_ONCE(rdp->mynode->completed) !=
+		    READ_ONCE(rdp->cond_resched_completed))
 			continue;
 
 		/*
@@ -491,9 +527,9 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
 		break;
 	}
 	if (rsp != NULL) {
-		*flags = ACCESS_ONCE(rsp->gp_flags);
-		*gpnum = ACCESS_ONCE(rsp->gpnum);
-		*completed = ACCESS_ONCE(rsp->completed);
+		*flags = READ_ONCE(rsp->gp_flags);
+		*gpnum = READ_ONCE(rsp->gpnum);
+		*completed = READ_ONCE(rsp->completed);
 		return;
 	}
 	*flags = 0;
@@ -539,10 +575,10 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp)
 static int rcu_future_needs_gp(struct rcu_state *rsp)
 {
 	struct rcu_node *rnp = rcu_get_root(rsp);
-	int idx = (ACCESS_ONCE(rnp->completed) + 1) & 0x1;
+	int idx = (READ_ONCE(rnp->completed) + 1) & 0x1;
 	int *fp = &rnp->need_future_gp[idx];
 
-	return ACCESS_ONCE(*fp);
+	return READ_ONCE(*fp);
 }
 
 /*
@@ -565,7 +601,7 @@ cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
 		return 1;  /* Yes, this CPU has newly registered callbacks. */
 	for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++)
 		if (rdp->nxttail[i - 1] != rdp->nxttail[i] &&
-		    ULONG_CMP_LT(ACCESS_ONCE(rsp->completed),
+		    ULONG_CMP_LT(READ_ONCE(rsp->completed),
 				 rdp->nxtcompleted[i]))
 			return 1;  /* Yes, CBs for future grace period. */
 	return 0; /* No grace period needed. */
@@ -585,7 +621,8 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
 	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
 
 	trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
-	if (!user && !is_idle_task(current)) {
+	if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+	    !user && !is_idle_task(current)) {
 		struct task_struct *idle __maybe_unused =
 			idle_task(smp_processor_id());
 
@@ -604,7 +641,8 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
 	smp_mb__before_atomic();  /* See above. */
 	atomic_inc(&rdtp->dynticks);
 	smp_mb__after_atomic();  /* Force ordering with next sojourn. */
-	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+		     atomic_read(&rdtp->dynticks) & 0x1);
 	rcu_dynticks_task_enter();
 
 	/*
@@ -630,7 +668,8 @@ static void rcu_eqs_enter(bool user)
 
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
-	WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+		     (oldval & DYNTICK_TASK_NEST_MASK) == 0);
 	if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) {
 		rdtp->dynticks_nesting = 0;
 		rcu_eqs_enter_common(oldval, user);
@@ -703,7 +742,8 @@ void rcu_irq_exit(void)
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	rdtp->dynticks_nesting--;
-	WARN_ON_ONCE(rdtp->dynticks_nesting < 0);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+		     rdtp->dynticks_nesting < 0);
 	if (rdtp->dynticks_nesting)
 		trace_rcu_dyntick(TPS("--="), oldval, rdtp->dynticks_nesting);
 	else
@@ -728,10 +768,12 @@ static void rcu_eqs_exit_common(long long oldval, int user)
 	atomic_inc(&rdtp->dynticks);
 	/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
 	smp_mb__after_atomic();  /* See above. */
-	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+		     !(atomic_read(&rdtp->dynticks) & 0x1));
 	rcu_cleanup_after_idle();
 	trace_rcu_dyntick(TPS("End"), oldval, rdtp->dynticks_nesting);
-	if (!user && !is_idle_task(current)) {
+	if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+	    !user && !is_idle_task(current)) {
 		struct task_struct *idle __maybe_unused =
 			idle_task(smp_processor_id());
 
@@ -755,7 +797,7 @@ static void rcu_eqs_exit(bool user)
 
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
-	WARN_ON_ONCE(oldval < 0);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0);
 	if (oldval & DYNTICK_TASK_NEST_MASK) {
 		rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE;
 	} else {
@@ -828,7 +870,8 @@ void rcu_irq_enter(void)
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	rdtp->dynticks_nesting++;
-	WARN_ON_ONCE(rdtp->dynticks_nesting == 0);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
+		     rdtp->dynticks_nesting == 0);
 	if (oldval)
 		trace_rcu_dyntick(TPS("++="), oldval, rdtp->dynticks_nesting);
 	else
@@ -1011,9 +1054,9 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp,
 		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
 		return 1;
 	} else {
-		if (ULONG_CMP_LT(ACCESS_ONCE(rdp->gpnum) + ULONG_MAX / 4,
+		if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4,
 				 rdp->mynode->gpnum))
-			ACCESS_ONCE(rdp->gpwrap) = true;
+			WRITE_ONCE(rdp->gpwrap, true);
 		return 0;
 	}
 }
@@ -1093,12 +1136,12 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 	if (ULONG_CMP_GE(jiffies,
 			 rdp->rsp->gp_start + jiffies_till_sched_qs) ||
 	    ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
-		if (!(ACCESS_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) {
-			ACCESS_ONCE(rdp->cond_resched_completed) =
-				ACCESS_ONCE(rdp->mynode->completed);
+		if (!(READ_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) {
+			WRITE_ONCE(rdp->cond_resched_completed,
+				   READ_ONCE(rdp->mynode->completed));
 			smp_mb(); /* ->cond_resched_completed before *rcrmp. */
-			ACCESS_ONCE(*rcrmp) =
-				ACCESS_ONCE(*rcrmp) + rdp->rsp->flavor_mask;
+			WRITE_ONCE(*rcrmp,
+				   READ_ONCE(*rcrmp) + rdp->rsp->flavor_mask);
 			resched_cpu(rdp->cpu);  /* Force CPU into scheduler. */
 			rdp->rsp->jiffies_resched += 5; /* Enable beating. */
 		} else if (ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
@@ -1119,9 +1162,9 @@ static void record_gp_stall_check_time(struct rcu_state *rsp)
 	rsp->gp_start = j;
 	smp_wmb(); /* Record start time before stall time. */
 	j1 = rcu_jiffies_till_stall_check();
-	ACCESS_ONCE(rsp->jiffies_stall) = j + j1;
+	WRITE_ONCE(rsp->jiffies_stall, j + j1);
 	rsp->jiffies_resched = j + j1 / 2;
-	rsp->n_force_qs_gpstart = ACCESS_ONCE(rsp->n_force_qs);
+	rsp->n_force_qs_gpstart = READ_ONCE(rsp->n_force_qs);
 }
 
 /*
@@ -1133,10 +1176,11 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
 	unsigned long j;
 
 	j = jiffies;
-	gpa = ACCESS_ONCE(rsp->gp_activity);
+	gpa = READ_ONCE(rsp->gp_activity);
 	if (j - gpa > 2 * HZ)
-		pr_err("%s kthread starved for %ld jiffies!\n",
-		       rsp->name, j - gpa);
+		pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x\n",
+		       rsp->name, j - gpa,
+		       rsp->gpnum, rsp->completed, rsp->gp_flags);
 }
 
 /*
@@ -1173,12 +1217,13 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 	/* Only let one CPU complain about others per time interval. */
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
-	delta = jiffies - ACCESS_ONCE(rsp->jiffies_stall);
+	delta = jiffies - READ_ONCE(rsp->jiffies_stall);
 	if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
 	}
-	ACCESS_ONCE(rsp->jiffies_stall) = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
+	WRITE_ONCE(rsp->jiffies_stall,
+		   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
 	/*
@@ -1212,12 +1257,12 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 	if (ndetected) {
 		rcu_dump_cpu_stacks(rsp);
 	} else {
-		if (ACCESS_ONCE(rsp->gpnum) != gpnum ||
-		    ACCESS_ONCE(rsp->completed) == gpnum) {
+		if (READ_ONCE(rsp->gpnum) != gpnum ||
+		    READ_ONCE(rsp->completed) == gpnum) {
 			pr_err("INFO: Stall ended before state dump start\n");
 		} else {
 			j = jiffies;
-			gpa = ACCESS_ONCE(rsp->gp_activity);
+			gpa = READ_ONCE(rsp->gp_activity);
 			pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n",
 			       rsp->name, j - gpa, j, gpa,
 			       jiffies_till_next_fqs,
@@ -1262,9 +1307,9 @@ static void print_cpu_stall(struct rcu_state *rsp)
 	rcu_dump_cpu_stacks(rsp);
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
-	if (ULONG_CMP_GE(jiffies, ACCESS_ONCE(rsp->jiffies_stall)))
-		ACCESS_ONCE(rsp->jiffies_stall) = jiffies +
-				     3 * rcu_jiffies_till_stall_check() + 3;
+	if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
+		WRITE_ONCE(rsp->jiffies_stall,
+			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
 	/*
@@ -1307,20 +1352,20 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 	 * Given this check, comparisons of jiffies, rsp->jiffies_stall,
 	 * and rsp->gp_start suffice to forestall false positives.
 	 */
-	gpnum = ACCESS_ONCE(rsp->gpnum);
+	gpnum = READ_ONCE(rsp->gpnum);
 	smp_rmb(); /* Pick up ->gpnum first... */
-	js = ACCESS_ONCE(rsp->jiffies_stall);
+	js = READ_ONCE(rsp->jiffies_stall);
 	smp_rmb(); /* ...then ->jiffies_stall before the rest... */
-	gps = ACCESS_ONCE(rsp->gp_start);
+	gps = READ_ONCE(rsp->gp_start);
 	smp_rmb(); /* ...and finally ->gp_start before ->completed. */
-	completed = ACCESS_ONCE(rsp->completed);
+	completed = READ_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)) {
+	    (READ_ONCE(rnp->qsmask) & rdp->grpmask)) {
 
 		/* We haven't checked in, so go dump stack. */
 		print_cpu_stall(rsp);
@@ -1347,7 +1392,7 @@ void rcu_cpu_stall_reset(void)
 	struct rcu_state *rsp;
 
 	for_each_rcu_flavor(rsp)
-		ACCESS_ONCE(rsp->jiffies_stall) = jiffies + ULONG_MAX / 2;
+		WRITE_ONCE(rsp->jiffies_stall, jiffies + ULONG_MAX / 2);
 }
 
 /*
@@ -1457,7 +1502,7 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 	 * doing some extra useless work.
 	 */
 	if (rnp->gpnum != rnp->completed ||
-	    ACCESS_ONCE(rnp_root->gpnum) != ACCESS_ONCE(rnp_root->completed)) {
+	    READ_ONCE(rnp_root->gpnum) != READ_ONCE(rnp_root->completed)) {
 		rnp->need_future_gp[c & 0x1]++;
 		trace_rcu_future_gp(rnp, rdp, c, TPS("Startedleaf"));
 		goto out;
@@ -1542,7 +1587,7 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
 static void rcu_gp_kthread_wake(struct rcu_state *rsp)
 {
 	if (current == rsp->gp_kthread ||
-	    !ACCESS_ONCE(rsp->gp_flags) ||
+	    !READ_ONCE(rsp->gp_flags) ||
 	    !rsp->gp_kthread)
 		return;
 	wake_up(&rsp->gp_wq);
@@ -1677,7 +1722,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 
 	/* Handle the ends of any preceding grace periods first. */
 	if (rdp->completed == rnp->completed &&
-	    !unlikely(ACCESS_ONCE(rdp->gpwrap))) {
+	    !unlikely(READ_ONCE(rdp->gpwrap))) {
 
 		/* No grace period end, so just accelerate recent callbacks. */
 		ret = rcu_accelerate_cbs(rsp, rnp, rdp);
@@ -1692,7 +1737,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuend"));
 	}
 
-	if (rdp->gpnum != rnp->gpnum || unlikely(ACCESS_ONCE(rdp->gpwrap))) {
+	if (rdp->gpnum != rnp->gpnum || unlikely(READ_ONCE(rdp->gpwrap))) {
 		/*
 		 * If the current grace period is waiting for this CPU,
 		 * set up to detect a quiescent state, otherwise don't
@@ -1704,7 +1749,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 		rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
 		rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask);
 		zero_cpu_stall_ticks(rdp);
-		ACCESS_ONCE(rdp->gpwrap) = false;
+		WRITE_ONCE(rdp->gpwrap, false);
 	}
 	return ret;
 }
@@ -1717,9 +1762,9 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 
 	local_irq_save(flags);
 	rnp = rdp->mynode;
-	if ((rdp->gpnum == ACCESS_ONCE(rnp->gpnum) &&
-	     rdp->completed == ACCESS_ONCE(rnp->completed) &&
-	     !unlikely(ACCESS_ONCE(rdp->gpwrap))) || /* w/out lock. */
+	if ((rdp->gpnum == READ_ONCE(rnp->gpnum) &&
+	     rdp->completed == READ_ONCE(rnp->completed) &&
+	     !unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */
 	    !raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */
 		local_irq_restore(flags);
 		return;
@@ -1731,6 +1776,13 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 		rcu_gp_kthread_wake(rsp);
 }
 
+static void rcu_gp_slow(struct rcu_state *rsp, int delay)
+{
+	if (delay > 0 &&
+	    !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
+		schedule_timeout_uninterruptible(delay);
+}
+
 /*
  * Initialize a new grace period.  Return 0 if no grace period required.
  */
@@ -1740,15 +1792,15 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
-	ACCESS_ONCE(rsp->gp_activity) = jiffies;
+	WRITE_ONCE(rsp->gp_activity, jiffies);
 	raw_spin_lock_irq(&rnp->lock);
 	smp_mb__after_unlock_lock();
-	if (!ACCESS_ONCE(rsp->gp_flags)) {
+	if (!READ_ONCE(rsp->gp_flags)) {
 		/* Spurious wakeup, tell caller to go back to sleep.  */
 		raw_spin_unlock_irq(&rnp->lock);
 		return 0;
 	}
-	ACCESS_ONCE(rsp->gp_flags) = 0; /* Clear all flags: New grace period. */
+	WRITE_ONCE(rsp->gp_flags, 0); /* Clear all flags: New grace period. */
 
 	if (WARN_ON_ONCE(rcu_gp_in_progress(rsp))) {
 		/*
@@ -1773,6 +1825,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	 * will handle subsequent offline CPUs.
 	 */
 	rcu_for_each_leaf_node(rsp, rnp) {
+		rcu_gp_slow(rsp, gp_preinit_delay);
 		raw_spin_lock_irq(&rnp->lock);
 		smp_mb__after_unlock_lock();
 		if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
@@ -1829,14 +1882,15 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	 * process finishes, because this kthread handles both.
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
+		rcu_gp_slow(rsp, gp_init_delay);
 		raw_spin_lock_irq(&rnp->lock);
 		smp_mb__after_unlock_lock();
 		rdp = this_cpu_ptr(rsp->rda);
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
-		ACCESS_ONCE(rnp->gpnum) = rsp->gpnum;
+		WRITE_ONCE(rnp->gpnum, rsp->gpnum);
 		if (WARN_ON_ONCE(rnp->completed != rsp->completed))
-			ACCESS_ONCE(rnp->completed) = rsp->completed;
+			WRITE_ONCE(rnp->completed, rsp->completed);
 		if (rnp == rdp->mynode)
 			(void)__note_gp_changes(rsp, rnp, rdp);
 		rcu_preempt_boost_start_gp(rnp);
@@ -1845,10 +1899,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 					    rnp->grphi, rnp->qsmask);
 		raw_spin_unlock_irq(&rnp->lock);
 		cond_resched_rcu_qs();
-		ACCESS_ONCE(rsp->gp_activity) = jiffies;
-		if (gp_init_delay > 0 &&
-		    !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD)))
-			schedule_timeout_uninterruptible(gp_init_delay);
+		WRITE_ONCE(rsp->gp_activity, jiffies);
 	}
 
 	return 1;
@@ -1864,7 +1915,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 	unsigned long maxj;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
-	ACCESS_ONCE(rsp->gp_activity) = jiffies;
+	WRITE_ONCE(rsp->gp_activity, jiffies);
 	rsp->n_force_qs++;
 	if (fqs_state == RCU_SAVE_DYNTICK) {
 		/* Collect dyntick-idle snapshots. */
@@ -1882,11 +1933,11 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 		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) {
+	if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		raw_spin_lock_irq(&rnp->lock);
 		smp_mb__after_unlock_lock();
-		ACCESS_ONCE(rsp->gp_flags) =
-			ACCESS_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS;
+		WRITE_ONCE(rsp->gp_flags,
+			   READ_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS);
 		raw_spin_unlock_irq(&rnp->lock);
 	}
 	return fqs_state;
@@ -1903,7 +1954,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
-	ACCESS_ONCE(rsp->gp_activity) = jiffies;
+	WRITE_ONCE(rsp->gp_activity, jiffies);
 	raw_spin_lock_irq(&rnp->lock);
 	smp_mb__after_unlock_lock();
 	gp_duration = jiffies - rsp->gp_start;
@@ -1934,7 +1985,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 		smp_mb__after_unlock_lock();
 		WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
 		WARN_ON_ONCE(rnp->qsmask);
-		ACCESS_ONCE(rnp->completed) = rsp->gpnum;
+		WRITE_ONCE(rnp->completed, rsp->gpnum);
 		rdp = this_cpu_ptr(rsp->rda);
 		if (rnp == rdp->mynode)
 			needgp = __note_gp_changes(rsp, rnp, rdp) || needgp;
@@ -1942,7 +1993,8 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 		nocb += rcu_future_gp_cleanup(rsp, rnp);
 		raw_spin_unlock_irq(&rnp->lock);
 		cond_resched_rcu_qs();
-		ACCESS_ONCE(rsp->gp_activity) = jiffies;
+		WRITE_ONCE(rsp->gp_activity, jiffies);
+		rcu_gp_slow(rsp, gp_cleanup_delay);
 	}
 	rnp = rcu_get_root(rsp);
 	raw_spin_lock_irq(&rnp->lock);
@@ -1950,16 +2002,16 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	rcu_nocb_gp_set(rnp, nocb);
 
 	/* Declare grace period done. */
-	ACCESS_ONCE(rsp->completed) = rsp->gpnum;
+	WRITE_ONCE(rsp->completed, rsp->gpnum);
 	trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end"));
 	rsp->fqs_state = RCU_GP_IDLE;
 	rdp = this_cpu_ptr(rsp->rda);
 	/* Advance CBs to reduce false positives below. */
 	needgp = rcu_advance_cbs(rsp, rnp, rdp) || needgp;
 	if (needgp || cpu_needs_another_gp(rsp, rdp)) {
-		ACCESS_ONCE(rsp->gp_flags) = RCU_GP_FLAG_INIT;
+		WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
 		trace_rcu_grace_period(rsp->name,
-				       ACCESS_ONCE(rsp->gpnum),
+				       READ_ONCE(rsp->gpnum),
 				       TPS("newreq"));
 	}
 	raw_spin_unlock_irq(&rnp->lock);
@@ -1983,20 +2035,20 @@ static int __noreturn rcu_gp_kthread(void *arg)
 		/* Handle grace-period start. */
 		for (;;) {
 			trace_rcu_grace_period(rsp->name,
-					       ACCESS_ONCE(rsp->gpnum),
+					       READ_ONCE(rsp->gpnum),
 					       TPS("reqwait"));
 			rsp->gp_state = RCU_GP_WAIT_GPS;
 			wait_event_interruptible(rsp->gp_wq,
-						 ACCESS_ONCE(rsp->gp_flags) &
+						 READ_ONCE(rsp->gp_flags) &
 						 RCU_GP_FLAG_INIT);
 			/* Locking provides needed memory barrier. */
 			if (rcu_gp_init(rsp))
 				break;
 			cond_resched_rcu_qs();
-			ACCESS_ONCE(rsp->gp_activity) = jiffies;
+			WRITE_ONCE(rsp->gp_activity, jiffies);
 			WARN_ON(signal_pending(current));
 			trace_rcu_grace_period(rsp->name,
-					       ACCESS_ONCE(rsp->gpnum),
+					       READ_ONCE(rsp->gpnum),
 					       TPS("reqwaitsig"));
 		}
 
@@ -2012,39 +2064,39 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			if (!ret)
 				rsp->jiffies_force_qs = jiffies + j;
 			trace_rcu_grace_period(rsp->name,
-					       ACCESS_ONCE(rsp->gpnum),
+					       READ_ONCE(rsp->gpnum),
 					       TPS("fqswait"));
 			rsp->gp_state = RCU_GP_WAIT_FQS;
 			ret = wait_event_interruptible_timeout(rsp->gp_wq,
-					((gf = ACCESS_ONCE(rsp->gp_flags)) &
+					((gf = READ_ONCE(rsp->gp_flags)) &
 					 RCU_GP_FLAG_FQS) ||
-					(!ACCESS_ONCE(rnp->qsmask) &&
+					(!READ_ONCE(rnp->qsmask) &&
 					 !rcu_preempt_blocked_readers_cgp(rnp)),
 					j);
 			/* Locking provides needed memory barriers. */
 			/* If grace period done, leave loop. */
-			if (!ACCESS_ONCE(rnp->qsmask) &&
+			if (!READ_ONCE(rnp->qsmask) &&
 			    !rcu_preempt_blocked_readers_cgp(rnp))
 				break;
 			/* If time for quiescent-state forcing, do it. */
 			if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) ||
 			    (gf & RCU_GP_FLAG_FQS)) {
 				trace_rcu_grace_period(rsp->name,
-						       ACCESS_ONCE(rsp->gpnum),
+						       READ_ONCE(rsp->gpnum),
 						       TPS("fqsstart"));
 				fqs_state = rcu_gp_fqs(rsp, fqs_state);
 				trace_rcu_grace_period(rsp->name,
-						       ACCESS_ONCE(rsp->gpnum),
+						       READ_ONCE(rsp->gpnum),
 						       TPS("fqsend"));
 				cond_resched_rcu_qs();
-				ACCESS_ONCE(rsp->gp_activity) = jiffies;
+				WRITE_ONCE(rsp->gp_activity, jiffies);
 			} else {
 				/* Deal with stray signal. */
 				cond_resched_rcu_qs();
-				ACCESS_ONCE(rsp->gp_activity) = jiffies;
+				WRITE_ONCE(rsp->gp_activity, jiffies);
 				WARN_ON(signal_pending(current));
 				trace_rcu_grace_period(rsp->name,
-						       ACCESS_ONCE(rsp->gpnum),
+						       READ_ONCE(rsp->gpnum),
 						       TPS("fqswaitsig"));
 			}
 			j = jiffies_till_next_fqs;
@@ -2086,8 +2138,8 @@ rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp,
 		 */
 		return false;
 	}
-	ACCESS_ONCE(rsp->gp_flags) = RCU_GP_FLAG_INIT;
-	trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum),
+	WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
+	trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum),
 			       TPS("newreq"));
 
 	/*
@@ -2137,6 +2189,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
 	__releases(rcu_get_root(rsp)->lock)
 {
 	WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
+	WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS);
 	raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
 	rcu_gp_kthread_wake(rsp);
 }
@@ -2334,8 +2387,6 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
 	rcu_report_qs_rdp(rdp->cpu, rsp, rdp);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-
 /*
  * Send the specified CPU's RCU callbacks to the orphanage.  The
  * specified CPU must be offline, and the caller must hold the
@@ -2346,7 +2397,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
 			  struct rcu_node *rnp, struct rcu_data *rdp)
 {
 	/* No-CBs CPUs do not have orphanable callbacks. */
-	if (rcu_is_nocb_cpu(rdp->cpu))
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || rcu_is_nocb_cpu(rdp->cpu))
 		return;
 
 	/*
@@ -2359,7 +2410,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp,
 		rsp->qlen += rdp->qlen;
 		rdp->n_cbs_orphaned += rdp->qlen;
 		rdp->qlen_lazy = 0;
-		ACCESS_ONCE(rdp->qlen) = 0;
+		WRITE_ONCE(rdp->qlen, 0);
 	}
 
 	/*
@@ -2405,7 +2456,8 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp, unsigned long flags)
 	struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
 
 	/* No-CBs CPUs are handled specially. */
-	if (rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
+	    rcu_nocb_adopt_orphan_cbs(rsp, rdp, flags))
 		return;
 
 	/* Do the accounting first. */
@@ -2452,6 +2504,9 @@ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
 	RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda));
 	RCU_TRACE(struct rcu_node *rnp = rdp->mynode);
 
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+		return;
+
 	RCU_TRACE(mask = rdp->grpmask);
 	trace_rcu_grace_period(rsp->name,
 			       rnp->gpnum + 1 - !!(rnp->qsmask & mask),
@@ -2480,7 +2535,8 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 	long mask;
 	struct rcu_node *rnp = rnp_leaf;
 
-	if (rnp->qsmaskinit || rcu_preempt_has_tasks(rnp))
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
+	    rnp->qsmaskinit || rcu_preempt_has_tasks(rnp))
 		return;
 	for (;;) {
 		mask = rnp->grpmask;
@@ -2511,6 +2567,9 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
 
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+		return;
+
 	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
 	mask = rdp->grpmask;
 	raw_spin_lock_irqsave(&rnp->lock, flags);
@@ -2532,6 +2591,9 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rdp->mynode;  /* Outgoing CPU's rdp & rnp. */
 
+	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
+		return;
+
 	/* Adjust any no-longer-needed kthreads. */
 	rcu_boost_kthread_setaffinity(rnp, -1);
 
@@ -2546,26 +2608,6 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 		  cpu, rdp->qlen, rdp->nxtlist);
 }
 
-#else /* #ifdef CONFIG_HOTPLUG_CPU */
-
-static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
-{
-}
-
-static void __maybe_unused rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
-{
-}
-
-static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
-{
-}
-
-static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
-{
-}
-
-#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */
-
 /*
  * Invoke any RCU callbacks that have made it to the end of their grace
  * period.  Thottle as specified by rdp->blimit.
@@ -2580,7 +2622,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 	/* If no callbacks are ready, just return. */
 	if (!cpu_has_callbacks_ready_to_invoke(rdp)) {
 		trace_rcu_batch_start(rsp->name, rdp->qlen_lazy, rdp->qlen, 0);
-		trace_rcu_batch_end(rsp->name, 0, !!ACCESS_ONCE(rdp->nxtlist),
+		trace_rcu_batch_end(rsp->name, 0, !!READ_ONCE(rdp->nxtlist),
 				    need_resched(), is_idle_task(current),
 				    rcu_is_callbacks_kthread());
 		return;
@@ -2636,7 +2678,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 	}
 	smp_mb(); /* List handling before counting for rcu_barrier(). */
 	rdp->qlen_lazy -= count_lazy;
-	ACCESS_ONCE(rdp->qlen) = rdp->qlen - count;
+	WRITE_ONCE(rdp->qlen, rdp->qlen - count);
 	rdp->n_cbs_invoked += count;
 
 	/* Reinstate batch limit if we have worked down the excess. */
@@ -2730,10 +2772,6 @@ static void force_qs_rnp(struct rcu_state *rsp,
 		mask = 0;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		smp_mb__after_unlock_lock();
-		if (!rcu_gp_in_progress(rsp)) {
-			raw_spin_unlock_irqrestore(&rnp->lock, flags);
-			return;
-		}
 		if (rnp->qsmask == 0) {
 			if (rcu_state_p == &rcu_sched_state ||
 			    rsp != rcu_state_p ||
@@ -2763,8 +2801,6 @@ static void force_qs_rnp(struct rcu_state *rsp,
 		bit = 1;
 		for (; cpu <= rnp->grphi; cpu++, bit <<= 1) {
 			if ((rnp->qsmask & bit) != 0) {
-				if ((rnp->qsmaskinit & bit) == 0)
-					*isidle = false; /* Pending hotplug. */
 				if (f(per_cpu_ptr(rsp->rda, cpu), isidle, maxj))
 					mask |= bit;
 			}
@@ -2793,7 +2829,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
 	/* Funnel through hierarchy to reduce memory contention. */
 	rnp = __this_cpu_read(rsp->rda->mynode);
 	for (; rnp != NULL; rnp = rnp->parent) {
-		ret = (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) ||
+		ret = (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) ||
 		      !raw_spin_trylock(&rnp->fqslock);
 		if (rnp_old != NULL)
 			raw_spin_unlock(&rnp_old->fqslock);
@@ -2809,13 +2845,12 @@ static void force_quiescent_state(struct rcu_state *rsp)
 	raw_spin_lock_irqsave(&rnp_old->lock, flags);
 	smp_mb__after_unlock_lock();
 	raw_spin_unlock(&rnp_old->fqslock);
-	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
+	if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		rsp->n_force_qs_lh++;
 		raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
 		return;  /* Someone beat us to it. */
 	}
-	ACCESS_ONCE(rsp->gp_flags) =
-		ACCESS_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS;
+	WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS);
 	raw_spin_unlock_irqrestore(&rnp_old->lock, flags);
 	rcu_gp_kthread_wake(rsp);
 }
@@ -2881,7 +2916,7 @@ static void rcu_process_callbacks(struct softirq_action *unused)
  */
 static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
 {
-	if (unlikely(!ACCESS_ONCE(rcu_scheduler_fully_active)))
+	if (unlikely(!READ_ONCE(rcu_scheduler_fully_active)))
 		return;
 	if (likely(!rsp->boost)) {
 		rcu_do_batch(rsp, rdp);
@@ -2972,7 +3007,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 	WARN_ON_ONCE((unsigned long)head & 0x1); /* Misaligned rcu_head! */
 	if (debug_rcu_head_queue(head)) {
 		/* Probable double call_rcu(), so leak the callback. */
-		ACCESS_ONCE(head->func) = rcu_leak_callback;
+		WRITE_ONCE(head->func, rcu_leak_callback);
 		WARN_ONCE(1, "__call_rcu(): Leaked duplicate callback\n");
 		return;
 	}
@@ -3011,7 +3046,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 		if (!likely(rdp->nxtlist))
 			init_default_callback_list(rdp);
 	}
-	ACCESS_ONCE(rdp->qlen) = rdp->qlen + 1;
+	WRITE_ONCE(rdp->qlen, rdp->qlen + 1);
 	if (lazy)
 		rdp->qlen_lazy++;
 	else
@@ -3287,7 +3322,7 @@ void synchronize_sched_expedited(void)
 	if (ULONG_CMP_GE((ulong)atomic_long_read(&rsp->expedited_start),
 			 (ulong)atomic_long_read(&rsp->expedited_done) +
 			 ULONG_MAX / 8)) {
-		synchronize_sched();
+		wait_rcu_gp(call_rcu_sched);
 		atomic_long_inc(&rsp->expedited_wrap);
 		return;
 	}
@@ -3450,14 +3485,14 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 	}
 
 	/* Has another RCU grace period completed?  */
-	if (ACCESS_ONCE(rnp->completed) != rdp->completed) { /* outside lock */
+	if (READ_ONCE(rnp->completed) != rdp->completed) { /* outside lock */
 		rdp->n_rp_gp_completed++;
 		return 1;
 	}
 
 	/* Has a new RCU grace period started? */
-	if (ACCESS_ONCE(rnp->gpnum) != rdp->gpnum ||
-	    unlikely(ACCESS_ONCE(rdp->gpwrap))) { /* outside lock */
+	if (READ_ONCE(rnp->gpnum) != rdp->gpnum ||
+	    unlikely(READ_ONCE(rdp->gpwrap))) { /* outside lock */
 		rdp->n_rp_gp_started++;
 		return 1;
 	}
@@ -3493,7 +3528,7 @@ static int rcu_pending(void)
  * non-NULL, store an indication of whether all callbacks are lazy.
  * (If there are no callbacks, all of them are deemed to be lazy.)
  */
-static int __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy)
+static bool __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy)
 {
 	bool al = true;
 	bool hc = false;
@@ -3564,7 +3599,7 @@ static void _rcu_barrier(struct rcu_state *rsp)
 {
 	int cpu;
 	struct rcu_data *rdp;
-	unsigned long snap = ACCESS_ONCE(rsp->n_barrier_done);
+	unsigned long snap = READ_ONCE(rsp->n_barrier_done);
 	unsigned long snap_done;
 
 	_rcu_barrier_trace(rsp, "Begin", -1, snap);
@@ -3606,10 +3641,10 @@ static void _rcu_barrier(struct rcu_state *rsp)
 
 	/*
 	 * Increment ->n_barrier_done to avoid duplicate work.  Use
-	 * ACCESS_ONCE() to prevent the compiler from speculating
+	 * WRITE_ONCE() to prevent the compiler from speculating
 	 * the increment to precede the early-exit check.
 	 */
-	ACCESS_ONCE(rsp->n_barrier_done) = rsp->n_barrier_done + 1;
+	WRITE_ONCE(rsp->n_barrier_done, rsp->n_barrier_done + 1);
 	WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 1);
 	_rcu_barrier_trace(rsp, "Inc1", -1, rsp->n_barrier_done);
 	smp_mb(); /* Order ->n_barrier_done increment with below mechanism. */
@@ -3645,7 +3680,7 @@ static void _rcu_barrier(struct rcu_state *rsp)
 				__call_rcu(&rdp->barrier_head,
 					   rcu_barrier_callback, rsp, cpu, 0);
 			}
-		} else if (ACCESS_ONCE(rdp->qlen)) {
+		} else if (READ_ONCE(rdp->qlen)) {
 			_rcu_barrier_trace(rsp, "OnlineQ", cpu,
 					   rsp->n_barrier_done);
 			smp_call_function_single(cpu, rcu_barrier_func, rsp, 1);
@@ -3665,7 +3700,7 @@ static void _rcu_barrier(struct rcu_state *rsp)
 
 	/* Increment ->n_barrier_done to prevent duplicate work. */
 	smp_mb(); /* Keep increment after above mechanism. */
-	ACCESS_ONCE(rsp->n_barrier_done) = rsp->n_barrier_done + 1;
+	WRITE_ONCE(rsp->n_barrier_done, rsp->n_barrier_done + 1);
 	WARN_ON_ONCE((rsp->n_barrier_done & 0x1) != 0);
 	_rcu_barrier_trace(rsp, "Inc2", -1, rsp->n_barrier_done);
 	smp_mb(); /* Keep increment before caller's subsequent code. */
@@ -3780,7 +3815,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
 	rdp->completed = rnp->completed;
 	rdp->passed_quiesce = false;
-	rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
+	rdp->rcu_qs_ctr_snap = per_cpu(rcu_qs_ctr, cpu);
 	rdp->qs_pending = false;
 	trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -3924,16 +3959,16 @@ void rcu_scheduler_starting(void)
 
 /*
  * Compute the per-level fanout, either using the exact fanout specified
- * or balancing the tree, depending on CONFIG_RCU_FANOUT_EXACT.
+ * or balancing the tree, depending on the rcu_fanout_exact boot parameter.
  */
 static void __init rcu_init_levelspread(struct rcu_state *rsp)
 {
 	int i;
 
-	if (IS_ENABLED(CONFIG_RCU_FANOUT_EXACT)) {
+	if (rcu_fanout_exact) {
 		rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
 		for (i = rcu_num_lvls - 2; i >= 0; i--)
-			rsp->levelspread[i] = CONFIG_RCU_FANOUT;
+			rsp->levelspread[i] = RCU_FANOUT;
 	} else {
 		int ccur;
 		int cprv;
@@ -3971,9 +4006,9 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 
 	BUILD_BUG_ON(MAX_RCU_LVLS > ARRAY_SIZE(buf));  /* Fix buf[] init! */
 
-	/* Silence gcc 4.8 warning about array index out of range. */
-	if (rcu_num_lvls > RCU_NUM_LVLS)
-		panic("rcu_init_one: rcu_num_lvls overflow");
+	/* Silence gcc 4.8 false positive about array index out of range. */
+	if (rcu_num_lvls <= 0 || rcu_num_lvls > RCU_NUM_LVLS)
+		panic("rcu_init_one: rcu_num_lvls out of range");
 
 	/* Initialize the level-tracking arrays. */
 
@@ -4059,7 +4094,7 @@ static void __init rcu_init_geometry(void)
 		jiffies_till_next_fqs = d;
 
 	/* If the compile-time values are accurate, just leave. */
-	if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF &&
+	if (rcu_fanout_leaf == RCU_FANOUT_LEAF &&
 	    nr_cpu_ids == NR_CPUS)
 		return;
 	pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%d\n",
@@ -4073,7 +4108,7 @@ static void __init rcu_init_geometry(void)
 	rcu_capacity[0] = 1;
 	rcu_capacity[1] = rcu_fanout_leaf;
 	for (i = 2; i <= MAX_RCU_LVLS; i++)
-		rcu_capacity[i] = rcu_capacity[i - 1] * CONFIG_RCU_FANOUT;
+		rcu_capacity[i] = rcu_capacity[i - 1] * RCU_FANOUT;
 
 	/*
 	 * The boot-time rcu_fanout_leaf parameter is only permitted
@@ -4083,7 +4118,7 @@ static void __init rcu_init_geometry(void)
 	 * the configured number of CPUs.  Complain and fall back to the
 	 * compile-time values if these limits are exceeded.
 	 */
-	if (rcu_fanout_leaf < CONFIG_RCU_FANOUT_LEAF ||
+	if (rcu_fanout_leaf < RCU_FANOUT_LEAF ||
 	    rcu_fanout_leaf > sizeof(unsigned long) * 8 ||
 	    n > rcu_capacity[MAX_RCU_LVLS]) {
 		WARN_ON(1);
@@ -4109,6 +4144,28 @@ static void __init rcu_init_geometry(void)
 	rcu_num_nodes -= n;
 }
 
+/*
+ * Dump out the structure of the rcu_node combining tree associated
+ * with the rcu_state structure referenced by rsp.
+ */
+static void __init rcu_dump_rcu_node_tree(struct rcu_state *rsp)
+{
+	int level = 0;
+	struct rcu_node *rnp;
+
+	pr_info("rcu_node tree layout dump\n");
+	pr_info(" ");
+	rcu_for_each_node_breadth_first(rsp, rnp) {
+		if (rnp->level != level) {
+			pr_cont("\n");
+			pr_info(" ");
+			level = rnp->level;
+		}
+		pr_cont("%d:%d ^%d  ", rnp->grplo, rnp->grphi, rnp->grpnum);
+	}
+	pr_cont("\n");
+}
+
 void __init rcu_init(void)
 {
 	int cpu;
@@ -4119,6 +4176,8 @@ void __init rcu_init(void)
 	rcu_init_geometry();
 	rcu_init_one(&rcu_bh_state, &rcu_bh_data);
 	rcu_init_one(&rcu_sched_state, &rcu_sched_data);
+	if (dump_tree)
+		rcu_dump_rcu_node_tree(&rcu_sched_state);
 	__rcu_init_preempt();
 	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index a69d3da..4adb7ca 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -35,11 +35,33 @@
  * In practice, this did work well going from three levels to four.
  * Of course, your mileage may vary.
  */
+
 #define MAX_RCU_LVLS 4
-#define RCU_FANOUT_1	      (CONFIG_RCU_FANOUT_LEAF)
-#define RCU_FANOUT_2	      (RCU_FANOUT_1 * CONFIG_RCU_FANOUT)
-#define RCU_FANOUT_3	      (RCU_FANOUT_2 * CONFIG_RCU_FANOUT)
-#define RCU_FANOUT_4	      (RCU_FANOUT_3 * CONFIG_RCU_FANOUT)
+
+#ifdef CONFIG_RCU_FANOUT
+#define RCU_FANOUT CONFIG_RCU_FANOUT
+#else /* #ifdef CONFIG_RCU_FANOUT */
+# ifdef CONFIG_64BIT
+# define RCU_FANOUT 64
+# else
+# define RCU_FANOUT 32
+# endif
+#endif /* #else #ifdef CONFIG_RCU_FANOUT */
+
+#ifdef CONFIG_RCU_FANOUT_LEAF
+#define RCU_FANOUT_LEAF CONFIG_RCU_FANOUT_LEAF
+#else /* #ifdef CONFIG_RCU_FANOUT_LEAF */
+# ifdef CONFIG_64BIT
+# define RCU_FANOUT_LEAF 64
+# else
+# define RCU_FANOUT_LEAF 32
+# endif
+#endif /* #else #ifdef CONFIG_RCU_FANOUT_LEAF */
+
+#define RCU_FANOUT_1	      (RCU_FANOUT_LEAF)
+#define RCU_FANOUT_2	      (RCU_FANOUT_1 * RCU_FANOUT)
+#define RCU_FANOUT_3	      (RCU_FANOUT_2 * RCU_FANOUT)
+#define RCU_FANOUT_4	      (RCU_FANOUT_3 * RCU_FANOUT)
 
 #if NR_CPUS <= RCU_FANOUT_1
 #  define RCU_NUM_LVLS	      1
@@ -170,7 +192,6 @@ struct rcu_node {
 				/*  if there is no such task.  If there */
 				/*  is no current expedited grace period, */
 				/*  then there can cannot be any such task. */
-#ifdef CONFIG_RCU_BOOST
 	struct list_head *boost_tasks;
 				/* Pointer to first task that needs to be */
 				/*  priority boosted, or NULL if no priority */
@@ -208,7 +229,6 @@ struct rcu_node {
 	unsigned long n_balk_nos;
 				/* Refused to boost: not sure why, though. */
 				/*  This can happen due to race conditions. */
-#endif /* #ifdef CONFIG_RCU_BOOST */
 #ifdef CONFIG_RCU_NOCB_CPU
 	wait_queue_head_t nocb_gp_wq[2];
 				/* Place for rcu_nocb_kthread() to wait GP. */
@@ -519,14 +539,11 @@ extern struct list_head rcu_struct_flavors;
  * RCU implementation internal declarations:
  */
 extern struct rcu_state rcu_sched_state;
-DECLARE_PER_CPU(struct rcu_data, rcu_sched_data);
 
 extern struct rcu_state rcu_bh_state;
-DECLARE_PER_CPU(struct rcu_data, rcu_bh_data);
 
 #ifdef CONFIG_PREEMPT_RCU
 extern struct rcu_state rcu_preempt_state;
-DECLARE_PER_CPU(struct rcu_data, rcu_preempt_data);
 #endif /* #ifdef CONFIG_PREEMPT_RCU */
 
 #ifdef CONFIG_RCU_BOOST
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 8c0ec0f..3266434 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -43,7 +43,17 @@ DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
 DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
 DEFINE_PER_CPU(char, rcu_cpu_has_work);
 
-#endif /* #ifdef CONFIG_RCU_BOOST */
+#else /* #ifdef CONFIG_RCU_BOOST */
+
+/*
+ * Some architectures do not define rt_mutexes, but if !CONFIG_RCU_BOOST,
+ * all uses are in dead code.  Provide a definition to keep the compiler
+ * happy, but add WARN_ON_ONCE() to complain if used in the wrong place.
+ * This probably needs to be excluded from -rt builds.
+ */
+#define rt_mutex_owner(a) ({ WARN_ON_ONCE(1); NULL; })
+
+#endif /* #else #ifdef CONFIG_RCU_BOOST */
 
 #ifdef CONFIG_RCU_NOCB_CPU
 static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */
@@ -60,11 +70,11 @@ static void __init rcu_bootup_announce_oddness(void)
 {
 	if (IS_ENABLED(CONFIG_RCU_TRACE))
 		pr_info("\tRCU debugfs-based tracing is enabled.\n");
-	if ((IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 64) ||
-	    (!IS_ENABLED(CONFIG_64BIT) && CONFIG_RCU_FANOUT != 32))
+	if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) ||
+	    (!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32))
 		pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
-		       CONFIG_RCU_FANOUT);
-	if (IS_ENABLED(CONFIG_RCU_FANOUT_EXACT))
+		       RCU_FANOUT);
+	if (rcu_fanout_exact)
 		pr_info("\tHierarchical RCU autobalancing is disabled.\n");
 	if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ))
 		pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n");
@@ -76,10 +86,10 @@ static void __init rcu_bootup_announce_oddness(void)
 		pr_info("\tAdditional per-CPU info printed with stalls.\n");
 	if (NUM_RCU_LVL_4 != 0)
 		pr_info("\tFour-level hierarchy is enabled.\n");
-	if (CONFIG_RCU_FANOUT_LEAF != 16)
+	if (RCU_FANOUT_LEAF != 16)
 		pr_info("\tBuild-time adjustment of leaf fanout to %d.\n",
-			CONFIG_RCU_FANOUT_LEAF);
-	if (rcu_fanout_leaf != CONFIG_RCU_FANOUT_LEAF)
+			RCU_FANOUT_LEAF);
+	if (rcu_fanout_leaf != RCU_FANOUT_LEAF)
 		pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
 	if (nr_cpu_ids != NR_CPUS)
 		pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%d.\n", NR_CPUS, nr_cpu_ids);
@@ -90,7 +100,8 @@ static void __init rcu_bootup_announce_oddness(void)
 #ifdef CONFIG_PREEMPT_RCU
 
 RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu);
-static struct rcu_state *rcu_state_p = &rcu_preempt_state;
+static struct rcu_state *const rcu_state_p = &rcu_preempt_state;
+static struct rcu_data __percpu *const rcu_data_p = &rcu_preempt_data;
 
 static int rcu_preempted_readers_exp(struct rcu_node *rnp);
 static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
@@ -116,11 +127,11 @@ static void __init rcu_bootup_announce(void)
  */
 static void rcu_preempt_qs(void)
 {
-	if (!__this_cpu_read(rcu_preempt_data.passed_quiesce)) {
+	if (!__this_cpu_read(rcu_data_p->passed_quiesce)) {
 		trace_rcu_grace_period(TPS("rcu_preempt"),
-				       __this_cpu_read(rcu_preempt_data.gpnum),
+				       __this_cpu_read(rcu_data_p->gpnum),
 				       TPS("cpuqs"));
-		__this_cpu_write(rcu_preempt_data.passed_quiesce, 1);
+		__this_cpu_write(rcu_data_p->passed_quiesce, 1);
 		barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */
 		current->rcu_read_unlock_special.b.need_qs = false;
 	}
@@ -150,7 +161,7 @@ static void rcu_preempt_note_context_switch(void)
 	    !t->rcu_read_unlock_special.b.blocked) {
 
 		/* Possibly blocking in an RCU read-side critical section. */
-		rdp = this_cpu_ptr(rcu_preempt_state.rda);
+		rdp = this_cpu_ptr(rcu_state_p->rda);
 		rnp = rdp->mynode;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
 		smp_mb__after_unlock_lock();
@@ -180,10 +191,9 @@ static void rcu_preempt_note_context_switch(void)
 		if ((rnp->qsmask & rdp->grpmask) && rnp->gp_tasks != NULL) {
 			list_add(&t->rcu_node_entry, rnp->gp_tasks->prev);
 			rnp->gp_tasks = &t->rcu_node_entry;
-#ifdef CONFIG_RCU_BOOST
-			if (rnp->boost_tasks != NULL)
+			if (IS_ENABLED(CONFIG_RCU_BOOST) &&
+			    rnp->boost_tasks != NULL)
 				rnp->boost_tasks = rnp->gp_tasks;
-#endif /* #ifdef CONFIG_RCU_BOOST */
 		} else {
 			list_add(&t->rcu_node_entry, &rnp->blkd_tasks);
 			if (rnp->qsmask & rdp->grpmask)
@@ -263,9 +273,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 	bool empty_exp_now;
 	unsigned long flags;
 	struct list_head *np;
-#ifdef CONFIG_RCU_BOOST
 	bool drop_boost_mutex = false;
-#endif /* #ifdef CONFIG_RCU_BOOST */
 	struct rcu_node *rnp;
 	union rcu_special special;
 
@@ -307,9 +315,11 @@ void rcu_read_unlock_special(struct task_struct *t)
 		t->rcu_read_unlock_special.b.blocked = false;
 
 		/*
-		 * Remove this task from the list it blocked on.  The
-		 * task can migrate while we acquire the lock, but at
-		 * most one time.  So at most two passes through loop.
+		 * Remove this task from the list it blocked on.  The task
+		 * now remains queued on the rcu_node corresponding to
+		 * the CPU it first blocked on, so the first attempt to
+		 * acquire the task's rcu_node's ->lock will succeed.
+		 * Keep the loop and add a WARN_ON() out of sheer paranoia.
 		 */
 		for (;;) {
 			rnp = t->rcu_blocked_node;
@@ -317,6 +327,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 			smp_mb__after_unlock_lock();
 			if (rnp == t->rcu_blocked_node)
 				break;
+			WARN_ON_ONCE(1);
 			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 		}
 		empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
@@ -331,12 +342,12 @@ void rcu_read_unlock_special(struct task_struct *t)
 			rnp->gp_tasks = np;
 		if (&t->rcu_node_entry == rnp->exp_tasks)
 			rnp->exp_tasks = np;
-#ifdef CONFIG_RCU_BOOST
-		if (&t->rcu_node_entry == rnp->boost_tasks)
-			rnp->boost_tasks = np;
-		/* Snapshot ->boost_mtx ownership with rcu_node lock held. */
-		drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t;
-#endif /* #ifdef CONFIG_RCU_BOOST */
+		if (IS_ENABLED(CONFIG_RCU_BOOST)) {
+			if (&t->rcu_node_entry == rnp->boost_tasks)
+				rnp->boost_tasks = np;
+			/* Snapshot ->boost_mtx ownership w/rnp->lock held. */
+			drop_boost_mutex = rt_mutex_owner(&rnp->boost_mtx) == t;
+		}
 
 		/*
 		 * If this was the last task on the current list, and if
@@ -353,24 +364,21 @@ void rcu_read_unlock_special(struct task_struct *t)
 							 rnp->grplo,
 							 rnp->grphi,
 							 !!rnp->gp_tasks);
-			rcu_report_unblock_qs_rnp(&rcu_preempt_state,
-						  rnp, flags);
+			rcu_report_unblock_qs_rnp(rcu_state_p, rnp, flags);
 		} else {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		}
 
-#ifdef CONFIG_RCU_BOOST
 		/* Unboost if we were boosted. */
-		if (drop_boost_mutex)
+		if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex)
 			rt_mutex_unlock(&rnp->boost_mtx);
-#endif /* #ifdef CONFIG_RCU_BOOST */
 
 		/*
 		 * If this was the last task on the expedited lists,
 		 * then we need to report up the rcu_node hierarchy.
 		 */
 		if (!empty_exp && empty_exp_now)
-			rcu_report_exp_rnp(&rcu_preempt_state, rnp, true);
+			rcu_report_exp_rnp(rcu_state_p, rnp, true);
 	} else {
 		local_irq_restore(flags);
 	}
@@ -390,7 +398,7 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
 	}
-	t = list_entry(rnp->gp_tasks,
+	t = list_entry(rnp->gp_tasks->prev,
 		       struct task_struct, rcu_node_entry);
 	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry)
 		sched_show_task(t);
@@ -447,7 +455,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp)
 	if (!rcu_preempt_blocked_readers_cgp(rnp))
 		return 0;
 	rcu_print_task_stall_begin(rnp);
-	t = list_entry(rnp->gp_tasks,
+	t = list_entry(rnp->gp_tasks->prev,
 		       struct task_struct, rcu_node_entry);
 	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
 		pr_cont(" P%d", t->pid);
@@ -491,8 +499,8 @@ static void rcu_preempt_check_callbacks(void)
 		return;
 	}
 	if (t->rcu_read_lock_nesting > 0 &&
-	    __this_cpu_read(rcu_preempt_data.qs_pending) &&
-	    !__this_cpu_read(rcu_preempt_data.passed_quiesce))
+	    __this_cpu_read(rcu_data_p->qs_pending) &&
+	    !__this_cpu_read(rcu_data_p->passed_quiesce))
 		t->rcu_read_unlock_special.b.need_qs = true;
 }
 
@@ -500,7 +508,7 @@ static void rcu_preempt_check_callbacks(void)
 
 static void rcu_preempt_do_callbacks(void)
 {
-	rcu_do_batch(&rcu_preempt_state, this_cpu_ptr(&rcu_preempt_data));
+	rcu_do_batch(rcu_state_p, this_cpu_ptr(rcu_data_p));
 }
 
 #endif /* #ifdef CONFIG_RCU_BOOST */
@@ -510,7 +518,7 @@ static void rcu_preempt_do_callbacks(void)
  */
 void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 {
-	__call_rcu(head, func, &rcu_preempt_state, -1, 0);
+	__call_rcu(head, func, rcu_state_p, -1, 0);
 }
 EXPORT_SYMBOL_GPL(call_rcu);
 
@@ -570,7 +578,7 @@ static int rcu_preempted_readers_exp(struct rcu_node *rnp)
 static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
 {
 	return !rcu_preempted_readers_exp(rnp) &&
-	       ACCESS_ONCE(rnp->expmask) == 0;
+	       READ_ONCE(rnp->expmask) == 0;
 }
 
 /*
@@ -711,12 +719,12 @@ sync_rcu_preempt_exp_init2(struct rcu_state *rsp, struct rcu_node *rnp)
 void synchronize_rcu_expedited(void)
 {
 	struct rcu_node *rnp;
-	struct rcu_state *rsp = &rcu_preempt_state;
+	struct rcu_state *rsp = rcu_state_p;
 	unsigned long snap;
 	int trycount = 0;
 
 	smp_mb(); /* Caller's modifications seen first by other CPUs. */
-	snap = ACCESS_ONCE(sync_rcu_preempt_exp_count) + 1;
+	snap = READ_ONCE(sync_rcu_preempt_exp_count) + 1;
 	smp_mb(); /* Above access cannot bleed into critical section. */
 
 	/*
@@ -740,7 +748,7 @@ void synchronize_rcu_expedited(void)
 	 */
 	while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) {
 		if (ULONG_CMP_LT(snap,
-		    ACCESS_ONCE(sync_rcu_preempt_exp_count))) {
+		    READ_ONCE(sync_rcu_preempt_exp_count))) {
 			put_online_cpus();
 			goto mb_ret; /* Others did our work for us. */
 		}
@@ -752,7 +760,7 @@ void synchronize_rcu_expedited(void)
 			return;
 		}
 	}
-	if (ULONG_CMP_LT(snap, ACCESS_ONCE(sync_rcu_preempt_exp_count))) {
+	if (ULONG_CMP_LT(snap, READ_ONCE(sync_rcu_preempt_exp_count))) {
 		put_online_cpus();
 		goto unlock_mb_ret; /* Others did our work for us. */
 	}
@@ -780,8 +788,7 @@ void synchronize_rcu_expedited(void)
 
 	/* Clean up and exit. */
 	smp_mb(); /* ensure expedited GP seen before counter increment. */
-	ACCESS_ONCE(sync_rcu_preempt_exp_count) =
-					sync_rcu_preempt_exp_count + 1;
+	WRITE_ONCE(sync_rcu_preempt_exp_count, sync_rcu_preempt_exp_count + 1);
 unlock_mb_ret:
 	mutex_unlock(&sync_rcu_preempt_exp_mutex);
 mb_ret:
@@ -799,7 +806,7 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
  */
 void rcu_barrier(void)
 {
-	_rcu_barrier(&rcu_preempt_state);
+	_rcu_barrier(rcu_state_p);
 }
 EXPORT_SYMBOL_GPL(rcu_barrier);
 
@@ -808,7 +815,7 @@ EXPORT_SYMBOL_GPL(rcu_barrier);
  */
 static void __init __rcu_init_preempt(void)
 {
-	rcu_init_one(&rcu_preempt_state, &rcu_preempt_data);
+	rcu_init_one(rcu_state_p, rcu_data_p);
 }
 
 /*
@@ -831,7 +838,8 @@ void exit_rcu(void)
 
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
-static struct rcu_state *rcu_state_p = &rcu_sched_state;
+static struct rcu_state *const rcu_state_p = &rcu_sched_state;
+static struct rcu_data __percpu *const rcu_data_p = &rcu_sched_data;
 
 /*
  * Tell them what RCU they are running.
@@ -994,8 +1002,8 @@ static int rcu_boost(struct rcu_node *rnp)
 	struct task_struct *t;
 	struct list_head *tb;
 
-	if (ACCESS_ONCE(rnp->exp_tasks) == NULL &&
-	    ACCESS_ONCE(rnp->boost_tasks) == NULL)
+	if (READ_ONCE(rnp->exp_tasks) == NULL &&
+	    READ_ONCE(rnp->boost_tasks) == NULL)
 		return 0;  /* Nothing left to boost. */
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
@@ -1048,8 +1056,8 @@ static int rcu_boost(struct rcu_node *rnp)
 	rt_mutex_lock(&rnp->boost_mtx);
 	rt_mutex_unlock(&rnp->boost_mtx);  /* Then keep lockdep happy. */
 
-	return ACCESS_ONCE(rnp->exp_tasks) != NULL ||
-	       ACCESS_ONCE(rnp->boost_tasks) != NULL;
+	return READ_ONCE(rnp->exp_tasks) != NULL ||
+	       READ_ONCE(rnp->boost_tasks) != NULL;
 }
 
 /*
@@ -1173,7 +1181,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 	struct sched_param sp;
 	struct task_struct *t;
 
-	if (&rcu_preempt_state != rsp)
+	if (rcu_state_p != rsp)
 		return 0;
 
 	if (!rcu_scheduler_fully_active || rcu_rnp_online_cpus(rnp) == 0)
@@ -1367,13 +1375,12 @@ static void rcu_prepare_kthreads(int cpu)
  * Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs
  * any flavor of RCU.
  */
-#ifndef CONFIG_RCU_NOCB_CPU_ALL
 int rcu_needs_cpu(unsigned long *delta_jiffies)
 {
 	*delta_jiffies = ULONG_MAX;
-	return rcu_cpu_has_callbacks(NULL);
+	return IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)
+	       ? 0 : rcu_cpu_has_callbacks(NULL);
 }
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 
 /*
  * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up
@@ -1462,7 +1469,7 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
 		 * callbacks not yet ready to invoke.
 		 */
 		if ((rdp->completed != rnp->completed ||
-		     unlikely(ACCESS_ONCE(rdp->gpwrap))) &&
+		     unlikely(READ_ONCE(rdp->gpwrap))) &&
 		    rdp->nxttail[RCU_DONE_TAIL] != rdp->nxttail[RCU_NEXT_TAIL])
 			note_gp_changes(rsp, rdp);
 
@@ -1480,11 +1487,15 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
  *
  * The caller must have disabled interrupts.
  */
-#ifndef CONFIG_RCU_NOCB_CPU_ALL
 int rcu_needs_cpu(unsigned long *dj)
 {
 	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
 
+	if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)) {
+		*dj = ULONG_MAX;
+		return 0;
+	}
+
 	/* Snapshot to detect later posting of non-lazy callback. */
 	rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted;
 
@@ -1511,7 +1522,6 @@ int rcu_needs_cpu(unsigned long *dj)
 	}
 	return 0;
 }
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 
 /*
  * Prepare a CPU for idle from an RCU perspective.  The first major task
@@ -1525,7 +1535,6 @@ int rcu_needs_cpu(unsigned long *dj)
  */
 static void rcu_prepare_for_idle(void)
 {
-#ifndef CONFIG_RCU_NOCB_CPU_ALL
 	bool needwake;
 	struct rcu_data *rdp;
 	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
@@ -1533,8 +1542,11 @@ static void rcu_prepare_for_idle(void)
 	struct rcu_state *rsp;
 	int tne;
 
+	if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL))
+		return;
+
 	/* Handle nohz enablement switches conservatively. */
-	tne = ACCESS_ONCE(tick_nohz_active);
+	tne = READ_ONCE(tick_nohz_active);
 	if (tne != rdtp->tick_nohz_enabled_snap) {
 		if (rcu_cpu_has_callbacks(NULL))
 			invoke_rcu_core(); /* force nohz to see update. */
@@ -1580,7 +1592,6 @@ static void rcu_prepare_for_idle(void)
 		if (needwake)
 			rcu_gp_kthread_wake(rsp);
 	}
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 }
 
 /*
@@ -1590,12 +1601,11 @@ static void rcu_prepare_for_idle(void)
  */
 static void rcu_cleanup_after_idle(void)
 {
-#ifndef CONFIG_RCU_NOCB_CPU_ALL
-	if (rcu_is_nocb_cpu(smp_processor_id()))
+	if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) ||
+	    rcu_is_nocb_cpu(smp_processor_id()))
 		return;
 	if (rcu_try_advance_all_cbs())
 		invoke_rcu_core();
-#endif /* #ifndef CONFIG_RCU_NOCB_CPU_ALL */
 }
 
 /*
@@ -1760,7 +1770,7 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu)
 	       atomic_read(&rdtp->dynticks) & 0xfff,
 	       rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting,
 	       rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
-	       ACCESS_ONCE(rsp->n_force_qs) - rsp->n_force_qs_gpstart,
+	       READ_ONCE(rsp->n_force_qs) - rsp->n_force_qs_gpstart,
 	       fast_no_hz);
 }
 
@@ -1898,11 +1908,11 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force)
 {
 	struct rcu_data *rdp_leader = rdp->nocb_leader;
 
-	if (!ACCESS_ONCE(rdp_leader->nocb_kthread))
+	if (!READ_ONCE(rdp_leader->nocb_kthread))
 		return;
-	if (ACCESS_ONCE(rdp_leader->nocb_leader_sleep) || force) {
+	if (READ_ONCE(rdp_leader->nocb_leader_sleep) || force) {
 		/* Prior smp_mb__after_atomic() orders against prior enqueue. */
-		ACCESS_ONCE(rdp_leader->nocb_leader_sleep) = false;
+		WRITE_ONCE(rdp_leader->nocb_leader_sleep, false);
 		wake_up(&rdp_leader->nocb_wq);
 	}
 }
@@ -1934,14 +1944,14 @@ static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu)
 	ret = atomic_long_read(&rdp->nocb_q_count);
 
 #ifdef CONFIG_PROVE_RCU
-	rhp = ACCESS_ONCE(rdp->nocb_head);
+	rhp = READ_ONCE(rdp->nocb_head);
 	if (!rhp)
-		rhp = ACCESS_ONCE(rdp->nocb_gp_head);
+		rhp = READ_ONCE(rdp->nocb_gp_head);
 	if (!rhp)
-		rhp = ACCESS_ONCE(rdp->nocb_follower_head);
+		rhp = READ_ONCE(rdp->nocb_follower_head);
 
 	/* Having no rcuo kthread but CBs after scheduler starts is bad! */
-	if (!ACCESS_ONCE(rdp->nocb_kthread) && rhp &&
+	if (!READ_ONCE(rdp->nocb_kthread) && rhp &&
 	    rcu_scheduler_fully_active) {
 		/* RCU callback enqueued before CPU first came online??? */
 		pr_err("RCU: Never-onlined no-CBs CPU %d has CB %p\n",
@@ -1975,12 +1985,12 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp,
 	atomic_long_add(rhcount, &rdp->nocb_q_count);
 	/* rcu_barrier() relies on ->nocb_q_count add before xchg. */
 	old_rhpp = xchg(&rdp->nocb_tail, rhtp);
-	ACCESS_ONCE(*old_rhpp) = rhp;
+	WRITE_ONCE(*old_rhpp, rhp);
 	atomic_long_add(rhcount_lazy, &rdp->nocb_q_count_lazy);
 	smp_mb__after_atomic(); /* Store *old_rhpp before _wake test. */
 
 	/* If we are not being polled and there is a kthread, awaken it ... */
-	t = ACCESS_ONCE(rdp->nocb_kthread);
+	t = READ_ONCE(rdp->nocb_kthread);
 	if (rcu_nocb_poll || !t) {
 		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
 				    TPS("WakeNotPoll"));
@@ -2118,7 +2128,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	for (;;) {
 		wait_event_interruptible(
 			rnp->nocb_gp_wq[c & 0x1],
-			(d = ULONG_CMP_GE(ACCESS_ONCE(rnp->completed), c)));
+			(d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c)));
 		if (likely(d))
 			break;
 		WARN_ON(signal_pending(current));
@@ -2145,7 +2155,7 @@ wait_again:
 	if (!rcu_nocb_poll) {
 		trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep");
 		wait_event_interruptible(my_rdp->nocb_wq,
-				!ACCESS_ONCE(my_rdp->nocb_leader_sleep));
+				!READ_ONCE(my_rdp->nocb_leader_sleep));
 		/* Memory barrier handled by smp_mb() calls below and repoll. */
 	} else if (firsttime) {
 		firsttime = false; /* Don't drown trace log with "Poll"! */
@@ -2159,12 +2169,12 @@ wait_again:
 	 */
 	gotcbs = false;
 	for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) {
-		rdp->nocb_gp_head = ACCESS_ONCE(rdp->nocb_head);
+		rdp->nocb_gp_head = READ_ONCE(rdp->nocb_head);
 		if (!rdp->nocb_gp_head)
 			continue;  /* No CBs here, try next follower. */
 
 		/* Move callbacks to wait-for-GP list, which is empty. */
-		ACCESS_ONCE(rdp->nocb_head) = NULL;
+		WRITE_ONCE(rdp->nocb_head, NULL);
 		rdp->nocb_gp_tail = xchg(&rdp->nocb_tail, &rdp->nocb_head);
 		gotcbs = true;
 	}
@@ -2184,7 +2194,7 @@ wait_again:
 		my_rdp->nocb_leader_sleep = true;
 		smp_mb();  /* Ensure _sleep true before scan. */
 		for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower)
-			if (ACCESS_ONCE(rdp->nocb_head)) {
+			if (READ_ONCE(rdp->nocb_head)) {
 				/* Found CB, so short-circuit next wait. */
 				my_rdp->nocb_leader_sleep = false;
 				break;
@@ -2205,7 +2215,7 @@ wait_again:
 
 	/* Each pass through the following loop wakes a follower, if needed. */
 	for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_follower) {
-		if (ACCESS_ONCE(rdp->nocb_head))
+		if (READ_ONCE(rdp->nocb_head))
 			my_rdp->nocb_leader_sleep = false;/* No need to sleep.*/
 		if (!rdp->nocb_gp_head)
 			continue; /* No CBs, so no need to wake follower. */
@@ -2241,7 +2251,7 @@ static void nocb_follower_wait(struct rcu_data *rdp)
 			trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu,
 					    "FollowerSleep");
 			wait_event_interruptible(rdp->nocb_wq,
-						 ACCESS_ONCE(rdp->nocb_follower_head));
+						 READ_ONCE(rdp->nocb_follower_head));
 		} else if (firsttime) {
 			/* Don't drown trace log with "Poll"! */
 			firsttime = false;
@@ -2282,10 +2292,10 @@ static int rcu_nocb_kthread(void *arg)
 			nocb_follower_wait(rdp);
 
 		/* Pull the ready-to-invoke callbacks onto local list. */
-		list = ACCESS_ONCE(rdp->nocb_follower_head);
+		list = READ_ONCE(rdp->nocb_follower_head);
 		BUG_ON(!list);
 		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "WokeNonEmpty");
-		ACCESS_ONCE(rdp->nocb_follower_head) = NULL;
+		WRITE_ONCE(rdp->nocb_follower_head, NULL);
 		tail = xchg(&rdp->nocb_follower_tail, &rdp->nocb_follower_head);
 
 		/* Each pass through the following loop invokes a callback. */
@@ -2324,7 +2334,7 @@ static int rcu_nocb_kthread(void *arg)
 /* Is a deferred wakeup of rcu_nocb_kthread() required? */
 static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp)
 {
-	return ACCESS_ONCE(rdp->nocb_defer_wakeup);
+	return READ_ONCE(rdp->nocb_defer_wakeup);
 }
 
 /* Do a deferred wakeup of rcu_nocb_kthread(). */
@@ -2334,8 +2344,8 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp)
 
 	if (!rcu_nocb_need_deferred_wakeup(rdp))
 		return;
-	ndw = ACCESS_ONCE(rdp->nocb_defer_wakeup);
-	ACCESS_ONCE(rdp->nocb_defer_wakeup) = RCU_NOGP_WAKE_NOT;
+	ndw = READ_ONCE(rdp->nocb_defer_wakeup);
+	WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOGP_WAKE_NOT);
 	wake_nocb_leader(rdp, ndw == RCU_NOGP_WAKE_FORCE);
 	trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWake"));
 }
@@ -2448,7 +2458,7 @@ static void rcu_spawn_one_nocb_kthread(struct rcu_state *rsp, int cpu)
 	t = kthread_run(rcu_nocb_kthread, rdp_spawn,
 			"rcuo%c/%d", rsp->abbr, cpu);
 	BUG_ON(IS_ERR(t));
-	ACCESS_ONCE(rdp_spawn->nocb_kthread) = t;
+	WRITE_ONCE(rdp_spawn->nocb_kthread, t);
 }
 
 /*
@@ -2663,7 +2673,7 @@ static void rcu_sysidle_enter(int irq)
 
 	/* Record start of fully idle period. */
 	j = jiffies;
-	ACCESS_ONCE(rdtp->dynticks_idle_jiffies) = j;
+	WRITE_ONCE(rdtp->dynticks_idle_jiffies, j);
 	smp_mb__before_atomic();
 	atomic_inc(&rdtp->dynticks_idle);
 	smp_mb__after_atomic();
@@ -2681,7 +2691,7 @@ static void rcu_sysidle_enter(int irq)
  */
 void rcu_sysidle_force_exit(void)
 {
-	int oldstate = ACCESS_ONCE(full_sysidle_state);
+	int oldstate = READ_ONCE(full_sysidle_state);
 	int newoldstate;
 
 	/*
@@ -2794,7 +2804,7 @@ static void rcu_sysidle_check_cpu(struct rcu_data *rdp, bool *isidle,
 	smp_mb(); /* Read counters before timestamps. */
 
 	/* Pick up timestamps. */
-	j = ACCESS_ONCE(rdtp->dynticks_idle_jiffies);
+	j = READ_ONCE(rdtp->dynticks_idle_jiffies);
 	/* If this CPU entered idle more recently, update maxj timestamp. */
 	if (ULONG_CMP_LT(*maxj, j))
 		*maxj = j;
@@ -2831,11 +2841,11 @@ static unsigned long rcu_sysidle_delay(void)
 static void rcu_sysidle(unsigned long j)
 {
 	/* Check the current state. */
-	switch (ACCESS_ONCE(full_sysidle_state)) {
+	switch (READ_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;
+		WRITE_ONCE(full_sysidle_state, RCU_SYSIDLE_SHORT);
 		break;
 
 	case RCU_SYSIDLE_SHORT:
@@ -2873,7 +2883,7 @@ static void rcu_sysidle_cancel(void)
 {
 	smp_mb();
 	if (full_sysidle_state > RCU_SYSIDLE_SHORT)
-		ACCESS_ONCE(full_sysidle_state) = RCU_SYSIDLE_NOT;
+		WRITE_ONCE(full_sysidle_state, RCU_SYSIDLE_NOT);
 }
 
 /*
@@ -2925,7 +2935,7 @@ static void rcu_sysidle_cb(struct rcu_head *rhp)
 	smp_mb();  /* grace period precedes setting inuse. */
 
 	rshp = container_of(rhp, struct rcu_sysidle_head, rh);
-	ACCESS_ONCE(rshp->inuse) = 0;
+	WRITE_ONCE(rshp->inuse, 0);
 }
 
 /*
@@ -2936,7 +2946,7 @@ static void rcu_sysidle_cb(struct rcu_head *rhp)
 bool rcu_sys_is_idle(void)
 {
 	static struct rcu_sysidle_head rsh;
-	int rss = ACCESS_ONCE(full_sysidle_state);
+	int rss = READ_ONCE(full_sysidle_state);
 
 	if (WARN_ON_ONCE(smp_processor_id() != tick_do_timer_cpu))
 		return false;
@@ -2964,7 +2974,7 @@ bool rcu_sys_is_idle(void)
 			}
 			rcu_sysidle_report(rcu_state_p, isidle, maxj, false);
 			oldrss = rss;
-			rss = ACCESS_ONCE(full_sysidle_state);
+			rss = READ_ONCE(full_sysidle_state);
 		}
 	}
 
@@ -3048,10 +3058,10 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
 #ifdef CONFIG_NO_HZ_FULL
 	if (tick_nohz_full_cpu(smp_processor_id()) &&
 	    (!rcu_gp_in_progress(rsp) ||
-	     ULONG_CMP_LT(jiffies, ACCESS_ONCE(rsp->gp_start) + HZ)))
-		return 1;
+	     ULONG_CMP_LT(jiffies, READ_ONCE(rsp->gp_start) + HZ)))
+		return true;
 #endif /* #ifdef CONFIG_NO_HZ_FULL */
-	return 0;
+	return false;
 }
 
 /*
@@ -3077,7 +3087,7 @@ static void rcu_bind_gp_kthread(void)
 static void rcu_dynticks_task_enter(void)
 {
 #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
-	ACCESS_ONCE(current->rcu_tasks_idle_cpu) = smp_processor_id();
+	WRITE_ONCE(current->rcu_tasks_idle_cpu, smp_processor_id());
 #endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
 }
 
@@ -3085,6 +3095,6 @@ static void rcu_dynticks_task_enter(void)
 static void rcu_dynticks_task_exit(void)
 {
 #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL)
-	ACCESS_ONCE(current->rcu_tasks_idle_cpu) = -1;
+	WRITE_ONCE(current->rcu_tasks_idle_cpu, -1);
 #endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */
 }
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index f92361e..3ea7ffc 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -277,7 +277,7 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp)
 	seq_printf(m, "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu oqlen=%ld/%ld\n",
 		   rsp->n_force_qs, rsp->n_force_qs_ngp,
 		   rsp->n_force_qs - rsp->n_force_qs_ngp,
-		   ACCESS_ONCE(rsp->n_force_qs_lh), rsp->qlen_lazy, rsp->qlen);
+		   READ_ONCE(rsp->n_force_qs_lh), rsp->qlen_lazy, rsp->qlen);
 	for (rnp = &rsp->node[0]; rnp - &rsp->node[0] < rcu_num_nodes; rnp++) {
 		if (rnp->level != level) {
 			seq_puts(m, "\n");
@@ -323,8 +323,8 @@ static void show_one_rcugp(struct seq_file *m, struct rcu_state *rsp)
 	struct rcu_node *rnp = &rsp->node[0];
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
-	completed = ACCESS_ONCE(rsp->completed);
-	gpnum = ACCESS_ONCE(rsp->gpnum);
+	completed = READ_ONCE(rsp->completed);
+	gpnum = READ_ONCE(rsp->gpnum);
 	if (completed == gpnum)
 		gpage = 0;
 	else
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 1f13335..afaecb7 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -150,14 +150,14 @@ void __rcu_read_unlock(void)
 		barrier();  /* critical section before exit code. */
 		t->rcu_read_lock_nesting = INT_MIN;
 		barrier();  /* assign before ->rcu_read_unlock_special load */
-		if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special.s)))
+		if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s)))
 			rcu_read_unlock_special(t);
 		barrier();  /* ->rcu_read_unlock_special load before assign */
 		t->rcu_read_lock_nesting = 0;
 	}
 #ifdef CONFIG_PROVE_LOCKING
 	{
-		int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting);
+		int rrln = READ_ONCE(t->rcu_read_lock_nesting);
 
 		WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2);
 	}
@@ -389,17 +389,17 @@ module_param(rcu_cpu_stall_timeout, int, 0644);
 
 int rcu_jiffies_till_stall_check(void)
 {
-	int till_stall_check = ACCESS_ONCE(rcu_cpu_stall_timeout);
+	int till_stall_check = READ_ONCE(rcu_cpu_stall_timeout);
 
 	/*
 	 * Limit check must be consistent with the Kconfig limits
 	 * for CONFIG_RCU_CPU_STALL_TIMEOUT.
 	 */
 	if (till_stall_check < 3) {
-		ACCESS_ONCE(rcu_cpu_stall_timeout) = 3;
+		WRITE_ONCE(rcu_cpu_stall_timeout, 3);
 		till_stall_check = 3;
 	} else if (till_stall_check > 300) {
-		ACCESS_ONCE(rcu_cpu_stall_timeout) = 300;
+		WRITE_ONCE(rcu_cpu_stall_timeout, 300);
 		till_stall_check = 300;
 	}
 	return till_stall_check * HZ + RCU_STALL_DELAY_DELTA;
@@ -550,12 +550,12 @@ static void check_holdout_task(struct task_struct *t,
 {
 	int cpu;
 
-	if (!ACCESS_ONCE(t->rcu_tasks_holdout) ||
-	    t->rcu_tasks_nvcsw != ACCESS_ONCE(t->nvcsw) ||
-	    !ACCESS_ONCE(t->on_rq) ||
+	if (!READ_ONCE(t->rcu_tasks_holdout) ||
+	    t->rcu_tasks_nvcsw != READ_ONCE(t->nvcsw) ||
+	    !READ_ONCE(t->on_rq) ||
 	    (IS_ENABLED(CONFIG_NO_HZ_FULL) &&
 	     !is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) {
-		ACCESS_ONCE(t->rcu_tasks_holdout) = false;
+		WRITE_ONCE(t->rcu_tasks_holdout, false);
 		list_del_init(&t->rcu_tasks_holdout_list);
 		put_task_struct(t);
 		return;
@@ -639,11 +639,11 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 		 */
 		rcu_read_lock();
 		for_each_process_thread(g, t) {
-			if (t != current && ACCESS_ONCE(t->on_rq) &&
+			if (t != current && READ_ONCE(t->on_rq) &&
 			    !is_idle_task(t)) {
 				get_task_struct(t);
-				t->rcu_tasks_nvcsw = ACCESS_ONCE(t->nvcsw);
-				ACCESS_ONCE(t->rcu_tasks_holdout) = true;
+				t->rcu_tasks_nvcsw = READ_ONCE(t->nvcsw);
+				WRITE_ONCE(t->rcu_tasks_holdout, true);
 				list_add(&t->rcu_tasks_holdout_list,
 					 &rcu_tasks_holdouts);
 			}
@@ -672,7 +672,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 			struct task_struct *t1;
 
 			schedule_timeout_interruptible(HZ);
-			rtst = ACCESS_ONCE(rcu_task_stall_timeout);
+			rtst = READ_ONCE(rcu_task_stall_timeout);
 			needreport = rtst > 0 &&
 				     time_after(jiffies, lastreport + rtst);
 			if (needreport)
@@ -728,7 +728,7 @@ static void rcu_spawn_tasks_kthread(void)
 	static struct task_struct *rcu_tasks_kthread_ptr;
 	struct task_struct *t;
 
-	if (ACCESS_ONCE(rcu_tasks_kthread_ptr)) {
+	if (READ_ONCE(rcu_tasks_kthread_ptr)) {
 		smp_mb(); /* Ensure caller sees full kthread. */
 		return;
 	}
@@ -740,7 +740,7 @@ static void rcu_spawn_tasks_kthread(void)
 	t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread");
 	BUG_ON(IS_ERR(t));
 	smp_mb(); /* Ensure others see full kthread. */
-	ACCESS_ONCE(rcu_tasks_kthread_ptr) = t;
+	WRITE_ONCE(rcu_tasks_kthread_ptr, t);
 	mutex_unlock(&rcu_tasks_kthread_mutex);
 }
 
diff --git a/kernel/torture.c b/kernel/torture.c
index dd70993..3e48406 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -409,7 +409,7 @@ static void (*torture_shutdown_hook)(void);
  */
 void torture_shutdown_absorb(const char *title)
 {
-	while (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
+	while (READ_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
 		pr_notice("torture thread %s parking due to system shutdown\n",
 			  title);
 		schedule_timeout_uninterruptible(MAX_SCHEDULE_TIMEOUT);
@@ -480,9 +480,9 @@ static int torture_shutdown_notify(struct notifier_block *unused1,
 				   unsigned long unused2, void *unused3)
 {
 	mutex_lock(&fullstop_mutex);
-	if (ACCESS_ONCE(fullstop) == FULLSTOP_DONTSTOP) {
+	if (READ_ONCE(fullstop) == FULLSTOP_DONTSTOP) {
 		VERBOSE_TOROUT_STRING("Unscheduled system shutdown detected");
-		ACCESS_ONCE(fullstop) = FULLSTOP_SHUTDOWN;
+		WRITE_ONCE(fullstop, FULLSTOP_SHUTDOWN);
 	} else {
 		pr_warn("Concurrent rmmod and shutdown illegal!\n");
 	}
@@ -523,13 +523,13 @@ static int stutter;
  */
 void stutter_wait(const char *title)
 {
-	while (ACCESS_ONCE(stutter_pause_test) ||
-	       (torture_runnable && !ACCESS_ONCE(*torture_runnable))) {
+	while (READ_ONCE(stutter_pause_test) ||
+	       (torture_runnable && !READ_ONCE(*torture_runnable))) {
 		if (stutter_pause_test)
-			if (ACCESS_ONCE(stutter_pause_test) == 1)
+			if (READ_ONCE(stutter_pause_test) == 1)
 				schedule_timeout_interruptible(1);
 			else
-				while (ACCESS_ONCE(stutter_pause_test))
+				while (READ_ONCE(stutter_pause_test))
 					cond_resched();
 		else
 			schedule_timeout_interruptible(round_jiffies_relative(HZ));
@@ -549,14 +549,14 @@ static int torture_stutter(void *arg)
 		if (!torture_must_stop()) {
 			if (stutter > 1) {
 				schedule_timeout_interruptible(stutter - 1);
-				ACCESS_ONCE(stutter_pause_test) = 2;
+				WRITE_ONCE(stutter_pause_test, 2);
 			}
 			schedule_timeout_interruptible(1);
-			ACCESS_ONCE(stutter_pause_test) = 1;
+			WRITE_ONCE(stutter_pause_test, 1);
 		}
 		if (!torture_must_stop())
 			schedule_timeout_interruptible(stutter);
-		ACCESS_ONCE(stutter_pause_test) = 0;
+		WRITE_ONCE(stutter_pause_test, 0);
 		torture_shutdown_absorb("torture_stutter");
 	} while (!torture_must_stop());
 	torture_kthread_stopping("torture_stutter");
@@ -642,13 +642,13 @@ EXPORT_SYMBOL_GPL(torture_init_end);
 bool torture_cleanup_begin(void)
 {
 	mutex_lock(&fullstop_mutex);
-	if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
+	if (READ_ONCE(fullstop) == FULLSTOP_SHUTDOWN) {
 		pr_warn("Concurrent rmmod and shutdown illegal!\n");
 		mutex_unlock(&fullstop_mutex);
 		schedule_timeout_uninterruptible(10);
 		return true;
 	}
-	ACCESS_ONCE(fullstop) = FULLSTOP_RMMOD;
+	WRITE_ONCE(fullstop, FULLSTOP_RMMOD);
 	mutex_unlock(&fullstop_mutex);
 	torture_shutdown_cleanup();
 	torture_shuffle_cleanup();
@@ -681,7 +681,7 @@ EXPORT_SYMBOL_GPL(torture_must_stop);
  */
 bool torture_must_stop_irq(void)
 {
-	return ACCESS_ONCE(fullstop) != FULLSTOP_DONTSTOP;
+	return READ_ONCE(fullstop) != FULLSTOP_DONTSTOP;
 }
 EXPORT_SYMBOL_GPL(torture_must_stop_irq);