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

Pull RCU updates from Ingo Molnar:
 "The main RCU changes in this cycle are:

   - the combination of tree geometry-initialization simplifications and
     OS-jitter-reduction changes to expedited grace periods.  These two
     are stacked due to the large number of conflicts that would
     otherwise result.

   - privatize smp_mb__after_unlock_lock().

     This commit moves the definition of smp_mb__after_unlock_lock() to
     kernel/rcu/tree.h, in recognition of the fact that RCU is the only
     thing using this, that nothing else is likely to use it, and that
     it is likely to go away completely.

   - documentation updates.

   - torture-test updates.

   - misc fixes"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (60 commits)
  rcu,locking: Privatize smp_mb__after_unlock_lock()
  rcu: Silence lockdep false positive for expedited grace periods
  rcu: Don't disable CPU hotplug during OOM notifiers
  scripts: Make checkpatch.pl warn on expedited RCU grace periods
  rcu: Update MAINTAINERS entry
  rcu: Clarify CONFIG_RCU_EQS_DEBUG help text
  rcu: Fix backwards RCU_LOCKDEP_WARN() in synchronize_rcu_tasks()
  rcu: Rename rcu_lockdep_assert() to RCU_LOCKDEP_WARN()
  rcu: Make rcu_is_watching() really notrace
  cpu: Wait for RCU grace periods concurrently
  rcu: Create a synchronize_rcu_mult()
  rcu: Fix obsolete priority-boosting comment
  rcu: Use WRITE_ONCE in RCU_INIT_POINTER
  rcu: Hide RCU_NOCB_CPU behind RCU_EXPERT
  rcu: Add RCU-sched flavors of get-state and cond-sync
  rcu: Add fastpath bypassing funnel locking
  rcu: Rename RCU_GP_DONE_FQS to RCU_GP_DOING_FQS
  rcu: Pull out wait_event*() condition into helper function
  documentation: Describe new expedited stall warnings
  rcu: Add stall warnings to synchronize_sched_expedited()
  ...

14 files changed, 632 insertions, 498 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index f89d9292eee6..b89f3168411b 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -107,8 +107,8 @@ static DEFINE_SPINLOCK(release_agent_path_lock);
 struct percpu_rw_semaphore cgroup_threadgroup_rwsem;
 
 #define cgroup_assert_mutex_or_rcu_locked()				\
-	rcu_lockdep_assert(rcu_read_lock_held() ||			\
-			   lockdep_is_held(&cgroup_mutex),		\
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
+			   !lockdep_is_held(&cgroup_mutex),		\
 			   "cgroup_mutex or RCU read lock required");
 
 /*
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 964b4efadf41..3c91a3fdfce5 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -382,14 +382,14 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen)
 	 * will observe it.
 	 *
 	 * For CONFIG_PREEMPT we have preemptible RCU and its sync_rcu() might
-	 * not imply sync_sched(), so explicitly call both.
+	 * not imply sync_sched(), so wait for both.
 	 *
 	 * Do sync before park smpboot threads to take care the rcu boost case.
 	 */
-#ifdef CONFIG_PREEMPT
-	synchronize_sched();
-#endif
-	synchronize_rcu();
+	if (IS_ENABLED(CONFIG_PREEMPT))
+		synchronize_rcu_mult(call_rcu, call_rcu_sched);
+	else
+		synchronize_rcu();
 
 	smpboot_park_threads(cpu);
 
diff --git a/kernel/pid.c b/kernel/pid.c
index 4fd07d5b7baf..ca368793808e 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -451,9 +451,8 @@ EXPORT_SYMBOL(pid_task);
  */
 struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns)
 {
-	rcu_lockdep_assert(rcu_read_lock_held(),
-			   "find_task_by_pid_ns() needs rcu_read_lock()"
-			   " protection");
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held(),
+			 "find_task_by_pid_ns() needs rcu_read_lock() protection");
 	return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID);
 }
 
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 59e32684c23b..77192953dee5 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -635,6 +635,8 @@ static struct rcu_torture_ops sched_ops = {
 	.deferred_free	= rcu_sched_torture_deferred_free,
 	.sync		= synchronize_sched,
 	.exp_sync	= synchronize_sched_expedited,
+	.get_state	= get_state_synchronize_sched,
+	.cond_sync	= cond_synchronize_sched,
 	.call		= call_rcu_sched,
 	.cb_barrier	= rcu_barrier_sched,
 	.fqs		= rcu_sched_force_quiescent_state,
@@ -684,10 +686,20 @@ static struct rcu_torture_ops tasks_ops = {
 
 #define RCUTORTURE_TASKS_OPS &tasks_ops,
 
+static bool __maybe_unused torturing_tasks(void)
+{
+	return cur_ops == &tasks_ops;
+}
+
 #else /* #ifdef CONFIG_TASKS_RCU */
 
 #define RCUTORTURE_TASKS_OPS
 
+static bool torturing_tasks(void)
+{
+	return false;
+}
+
 #endif /* #else #ifdef CONFIG_TASKS_RCU */
 
 /*
@@ -823,9 +835,7 @@ rcu_torture_cbflood(void *arg)
 	}
 	if (err) {
 		VERBOSE_TOROUT_STRING("rcu_torture_cbflood disabled: Bad args or OOM");
-		while (!torture_must_stop())
-			schedule_timeout_interruptible(HZ);
-		return 0;
+		goto wait_for_stop;
 	}
 	VERBOSE_TOROUT_STRING("rcu_torture_cbflood task started");
 	do {
@@ -844,6 +854,7 @@ rcu_torture_cbflood(void *arg)
 		stutter_wait("rcu_torture_cbflood");
 	} while (!torture_must_stop());
 	vfree(rhp);
+wait_for_stop:
 	torture_kthread_stopping("rcu_torture_cbflood");
 	return 0;
 }
@@ -1088,7 +1099,8 @@ 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_ctlp));
+				  srcu_read_lock_held(srcu_ctlp) ||
+				  torturing_tasks());
 	if (p == NULL) {
 		/* Leave because rcu_torture_writer is not yet underway */
 		cur_ops->readunlock(idx);
@@ -1162,7 +1174,8 @@ 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_ctlp));
+					  srcu_read_lock_held(srcu_ctlp) ||
+					  torturing_tasks());
 		if (p == NULL) {
 			/* Wait for rcu_torture_writer to get underway */
 			cur_ops->readunlock(idx);
@@ -1507,7 +1520,7 @@ static int rcu_torture_barrier_init(void)
 	int i;
 	int ret;
 
-	if (n_barrier_cbs == 0)
+	if (n_barrier_cbs <= 0)
 		return 0;
 	if (cur_ops->call == NULL || cur_ops->cb_barrier == NULL) {
 		pr_alert("%s" TORTURE_FLAG
@@ -1786,12 +1799,15 @@ rcu_torture_init(void)
 					  writer_task);
 	if (firsterr)
 		goto unwind;
-	fakewriter_tasks = kzalloc(nfakewriters * sizeof(fakewriter_tasks[0]),
-				   GFP_KERNEL);
-	if (fakewriter_tasks == NULL) {
-		VERBOSE_TOROUT_ERRSTRING("out of memory");
-		firsterr = -ENOMEM;
-		goto unwind;
+	if (nfakewriters > 0) {
+		fakewriter_tasks = kzalloc(nfakewriters *
+					   sizeof(fakewriter_tasks[0]),
+					   GFP_KERNEL);
+		if (fakewriter_tasks == NULL) {
+			VERBOSE_TOROUT_ERRSTRING("out of memory");
+			firsterr = -ENOMEM;
+			goto unwind;
+		}
 	}
 	for (i = 0; i < nfakewriters; i++) {
 		firsterr = torture_create_kthread(rcu_torture_fakewriter,
@@ -1818,7 +1834,7 @@ rcu_torture_init(void)
 		if (firsterr)
 			goto unwind;
 	}
-	if (test_no_idle_hz) {
+	if (test_no_idle_hz && shuffle_interval > 0) {
 		firsterr = torture_shuffle_init(shuffle_interval * HZ);
 		if (firsterr)
 			goto unwind;
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index fb33d35ee0b7..d3fcb2ec8536 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -252,14 +252,15 @@ static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx)
 }
 
 /**
- * srcu_readers_active - returns approximate number of readers.
+ * srcu_readers_active - returns true if there are readers. and false
+ *                       otherwise
  * @sp: which srcu_struct to count active readers (holding srcu_read_lock).
  *
  * Note that this is not an atomic primitive, and can therefore suffer
  * severe errors when invoked on an active srcu_struct.  That said, it
  * can be useful as an error check at cleanup time.
  */
-static int srcu_readers_active(struct srcu_struct *sp)
+static bool srcu_readers_active(struct srcu_struct *sp)
 {
 	int cpu;
 	unsigned long sum = 0;
@@ -414,11 +415,11 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
 	struct rcu_head *head = &rcu.head;
 	bool done = false;
 
-	rcu_lockdep_assert(!lock_is_held(&sp->dep_map) &&
-			   !lock_is_held(&rcu_bh_lock_map) &&
-			   !lock_is_held(&rcu_lock_map) &&
-			   !lock_is_held(&rcu_sched_lock_map),
-			   "Illegal synchronize_srcu() in same-type SRCU (or RCU) read-side critical section");
+	RCU_LOCKDEP_WARN(lock_is_held(&sp->dep_map) ||
+			 lock_is_held(&rcu_bh_lock_map) ||
+			 lock_is_held(&rcu_lock_map) ||
+			 lock_is_held(&rcu_sched_lock_map),
+			 "Illegal synchronize_srcu() in same-type SRCU (or in RCU) read-side critical section");
 
 	might_sleep();
 	init_completion(&rcu.completion);
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index c291bd65d2cb..d0471056d0af 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -191,10 +191,10 @@ static void rcu_process_callbacks(struct softirq_action *unused)
  */
 void synchronize_sched(void)
 {
-	rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) &&
-			   !lock_is_held(&rcu_lock_map) &&
-			   !lock_is_held(&rcu_sched_lock_map),
-			   "Illegal synchronize_sched() in RCU read-side critical section");
+	RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
+			 lock_is_held(&rcu_lock_map) ||
+			 lock_is_held(&rcu_sched_lock_map),
+			 "Illegal synchronize_sched() in RCU read-side critical section");
 	cond_resched();
 }
 EXPORT_SYMBOL_GPL(synchronize_sched);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 65137bc28b2b..9f75f25cc5d9 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -70,6 +70,8 @@ MODULE_ALIAS("rcutree");
 
 static struct lock_class_key rcu_node_class[RCU_NUM_LVLS];
 static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS];
+static struct lock_class_key rcu_exp_class[RCU_NUM_LVLS];
+static struct lock_class_key rcu_exp_sched_class[RCU_NUM_LVLS];
 
 /*
  * In order to export the rcu_state name to the tracing tools, it
@@ -124,13 +126,8 @@ module_param(rcu_fanout_exact, bool, 0444);
 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. */
-	NUM_RCU_LVL_0,
-	NUM_RCU_LVL_1,
-	NUM_RCU_LVL_2,
-	NUM_RCU_LVL_3,
-	NUM_RCU_LVL_4,
-};
+/* Number of rcu_nodes at specified level. */
+static int num_rcu_lvl[] = NUM_RCU_LVL_INIT;
 int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */
 
 /*
@@ -649,12 +646,12 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
 	 * It is illegal to enter an extended quiescent state while
 	 * in an RCU read-side critical section.
 	 */
-	rcu_lockdep_assert(!lock_is_held(&rcu_lock_map),
-			   "Illegal idle entry in RCU read-side critical section.");
-	rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map),
-			   "Illegal idle entry in RCU-bh read-side critical section.");
-	rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map),
-			   "Illegal idle entry in RCU-sched read-side critical section.");
+	RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map),
+			 "Illegal idle entry in RCU read-side critical section.");
+	RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map),
+			 "Illegal idle entry in RCU-bh read-side critical section.");
+	RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map),
+			 "Illegal idle entry in RCU-sched read-side critical section.");
 }
 
 /*
@@ -701,7 +698,7 @@ void rcu_idle_enter(void)
 }
 EXPORT_SYMBOL_GPL(rcu_idle_enter);
 
-#ifdef CONFIG_RCU_USER_QS
+#ifdef CONFIG_NO_HZ_FULL
 /**
  * rcu_user_enter - inform RCU that we are resuming userspace.
  *
@@ -714,7 +711,7 @@ void rcu_user_enter(void)
 {
 	rcu_eqs_enter(1);
 }
-#endif /* CONFIG_RCU_USER_QS */
+#endif /* CONFIG_NO_HZ_FULL */
 
 /**
  * rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle
@@ -828,7 +825,7 @@ void rcu_idle_exit(void)
 }
 EXPORT_SYMBOL_GPL(rcu_idle_exit);
 
-#ifdef CONFIG_RCU_USER_QS
+#ifdef CONFIG_NO_HZ_FULL
 /**
  * rcu_user_exit - inform RCU that we are exiting userspace.
  *
@@ -839,7 +836,7 @@ void rcu_user_exit(void)
 {
 	rcu_eqs_exit(1);
 }
-#endif /* CONFIG_RCU_USER_QS */
+#endif /* CONFIG_NO_HZ_FULL */
 
 /**
  * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle
@@ -978,9 +975,9 @@ bool notrace rcu_is_watching(void)
 {
 	bool ret;
 
-	preempt_disable();
+	preempt_disable_notrace();
 	ret = __rcu_is_watching();
-	preempt_enable();
+	preempt_enable_notrace();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(rcu_is_watching);
@@ -1178,9 +1175,11 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
 	j = jiffies;
 	gpa = READ_ONCE(rsp->gp_activity);
 	if (j - gpa > 2 * HZ)
-		pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x\n",
+		pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x s%d ->state=%#lx\n",
 		       rsp->name, j - gpa,
-		       rsp->gpnum, rsp->completed, rsp->gp_flags);
+		       rsp->gpnum, rsp->completed,
+		       rsp->gp_flags, rsp->gp_state,
+		       rsp->gp_kthread ? rsp->gp_kthread->state : 0);
 }
 
 /*
@@ -1906,6 +1905,26 @@ static int rcu_gp_init(struct rcu_state *rsp)
 }
 
 /*
+ * Helper function for wait_event_interruptible_timeout() wakeup
+ * at force-quiescent-state time.
+ */
+static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp)
+{
+	struct rcu_node *rnp = rcu_get_root(rsp);
+
+	/* Someone like call_rcu() requested a force-quiescent-state scan. */
+	*gfp = READ_ONCE(rsp->gp_flags);
+	if (*gfp & RCU_GP_FLAG_FQS)
+		return true;
+
+	/* The current grace period has completed. */
+	if (!READ_ONCE(rnp->qsmask) && !rcu_preempt_blocked_readers_cgp(rnp))
+		return true;
+
+	return false;
+}
+
+/*
  * Do one round of quiescent-state forcing.
  */
 static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
@@ -2041,6 +2060,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			wait_event_interruptible(rsp->gp_wq,
 						 READ_ONCE(rsp->gp_flags) &
 						 RCU_GP_FLAG_INIT);
+			rsp->gp_state = RCU_GP_DONE_GPS;
 			/* Locking provides needed memory barrier. */
 			if (rcu_gp_init(rsp))
 				break;
@@ -2068,11 +2088,8 @@ static int __noreturn rcu_gp_kthread(void *arg)
 					       TPS("fqswait"));
 			rsp->gp_state = RCU_GP_WAIT_FQS;
 			ret = wait_event_interruptible_timeout(rsp->gp_wq,
-					((gf = READ_ONCE(rsp->gp_flags)) &
-					 RCU_GP_FLAG_FQS) ||
-					(!READ_ONCE(rnp->qsmask) &&
-					 !rcu_preempt_blocked_readers_cgp(rnp)),
-					j);
+					rcu_gp_fqs_check_wake(rsp, &gf), j);
+			rsp->gp_state = RCU_GP_DOING_FQS;
 			/* Locking provides needed memory barriers. */
 			/* If grace period done, leave loop. */
 			if (!READ_ONCE(rnp->qsmask) &&
@@ -2110,7 +2127,9 @@ static int __noreturn rcu_gp_kthread(void *arg)
 		}
 
 		/* Handle grace-period end. */
+		rsp->gp_state = RCU_GP_CLEANUP;
 		rcu_gp_cleanup(rsp);
+		rsp->gp_state = RCU_GP_CLEANED;
 	}
 }
 
@@ -3161,10 +3180,10 @@ static inline int rcu_blocking_is_gp(void)
  */
 void synchronize_sched(void)
 {
-	rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) &&
-			   !lock_is_held(&rcu_lock_map) &&
-			   !lock_is_held(&rcu_sched_lock_map),
-			   "Illegal synchronize_sched() in RCU-sched read-side critical section");
+	RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
+			 lock_is_held(&rcu_lock_map) ||
+			 lock_is_held(&rcu_sched_lock_map),
+			 "Illegal synchronize_sched() in RCU-sched read-side critical section");
 	if (rcu_blocking_is_gp())
 		return;
 	if (rcu_gp_is_expedited())
@@ -3188,10 +3207,10 @@ EXPORT_SYMBOL_GPL(synchronize_sched);
  */
 void synchronize_rcu_bh(void)
 {
-	rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) &&
-			   !lock_is_held(&rcu_lock_map) &&
-			   !lock_is_held(&rcu_sched_lock_map),
-			   "Illegal synchronize_rcu_bh() in RCU-bh read-side critical section");
+	RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
+			 lock_is_held(&rcu_lock_map) ||
+			 lock_is_held(&rcu_sched_lock_map),
+			 "Illegal synchronize_rcu_bh() in RCU-bh read-side critical section");
 	if (rcu_blocking_is_gp())
 		return;
 	if (rcu_gp_is_expedited())
@@ -3253,23 +3272,247 @@ void cond_synchronize_rcu(unsigned long oldstate)
 }
 EXPORT_SYMBOL_GPL(cond_synchronize_rcu);
 
-static int synchronize_sched_expedited_cpu_stop(void *data)
+/**
+ * get_state_synchronize_sched - Snapshot current RCU-sched state
+ *
+ * Returns a cookie that is used by a later call to cond_synchronize_sched()
+ * to determine whether or not a full grace period has elapsed in the
+ * meantime.
+ */
+unsigned long get_state_synchronize_sched(void)
 {
 	/*
-	 * There must be a full memory barrier on each affected CPU
-	 * between the time that try_stop_cpus() is called and the
-	 * time that it returns.
-	 *
-	 * In the current initial implementation of cpu_stop, the
-	 * above condition is already met when the control reaches
-	 * this point and the following smp_mb() is not strictly
-	 * necessary.  Do smp_mb() anyway for documentation and
-	 * robustness against future implementation changes.
+	 * Any prior manipulation of RCU-protected data must happen
+	 * before the load from ->gpnum.
+	 */
+	smp_mb();  /* ^^^ */
+
+	/*
+	 * Make sure this load happens before the purportedly
+	 * time-consuming work between get_state_synchronize_sched()
+	 * and cond_synchronize_sched().
+	 */
+	return smp_load_acquire(&rcu_sched_state.gpnum);
+}
+EXPORT_SYMBOL_GPL(get_state_synchronize_sched);
+
+/**
+ * cond_synchronize_sched - Conditionally wait for an RCU-sched grace period
+ *
+ * @oldstate: return value from earlier call to get_state_synchronize_sched()
+ *
+ * If a full RCU-sched grace period has elapsed since the earlier call to
+ * get_state_synchronize_sched(), just return.  Otherwise, invoke
+ * synchronize_sched() to wait for a full grace period.
+ *
+ * Yes, this function does not take counter wrap into account.  But
+ * counter wrap is harmless.  If the counter wraps, we have waited for
+ * more than 2 billion grace periods (and way more on a 64-bit system!),
+ * so waiting for one additional grace period should be just fine.
+ */
+void cond_synchronize_sched(unsigned long oldstate)
+{
+	unsigned long newstate;
+
+	/*
+	 * Ensure that this load happens before any RCU-destructive
+	 * actions the caller might carry out after we return.
 	 */
-	smp_mb(); /* See above comment block. */
+	newstate = smp_load_acquire(&rcu_sched_state.completed);
+	if (ULONG_CMP_GE(oldstate, newstate))
+		synchronize_sched();
+}
+EXPORT_SYMBOL_GPL(cond_synchronize_sched);
+
+/* Adjust sequence number for start of update-side operation. */
+static void rcu_seq_start(unsigned long *sp)
+{
+	WRITE_ONCE(*sp, *sp + 1);
+	smp_mb(); /* Ensure update-side operation after counter increment. */
+	WARN_ON_ONCE(!(*sp & 0x1));
+}
+
+/* Adjust sequence number for end of update-side operation. */
+static void rcu_seq_end(unsigned long *sp)
+{
+	smp_mb(); /* Ensure update-side operation before counter increment. */
+	WRITE_ONCE(*sp, *sp + 1);
+	WARN_ON_ONCE(*sp & 0x1);
+}
+
+/* Take a snapshot of the update side's sequence number. */
+static unsigned long rcu_seq_snap(unsigned long *sp)
+{
+	unsigned long s;
+
+	smp_mb(); /* Caller's modifications seen first by other CPUs. */
+	s = (READ_ONCE(*sp) + 3) & ~0x1;
+	smp_mb(); /* Above access must not bleed into critical section. */
+	return s;
+}
+
+/*
+ * Given a snapshot from rcu_seq_snap(), determine whether or not a
+ * full update-side operation has occurred.
+ */
+static bool rcu_seq_done(unsigned long *sp, unsigned long s)
+{
+	return ULONG_CMP_GE(READ_ONCE(*sp), s);
+}
+
+/* Wrapper functions for expedited grace periods.  */
+static void rcu_exp_gp_seq_start(struct rcu_state *rsp)
+{
+	rcu_seq_start(&rsp->expedited_sequence);
+}
+static void rcu_exp_gp_seq_end(struct rcu_state *rsp)
+{
+	rcu_seq_end(&rsp->expedited_sequence);
+	smp_mb(); /* Ensure that consecutive grace periods serialize. */
+}
+static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp)
+{
+	return rcu_seq_snap(&rsp->expedited_sequence);
+}
+static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s)
+{
+	return rcu_seq_done(&rsp->expedited_sequence, s);
+}
+
+/* Common code for synchronize_{rcu,sched}_expedited() work-done checking. */
+static bool sync_exp_work_done(struct rcu_state *rsp, struct rcu_node *rnp,
+			       struct rcu_data *rdp,
+			       atomic_long_t *stat, unsigned long s)
+{
+	if (rcu_exp_gp_seq_done(rsp, s)) {
+		if (rnp)
+			mutex_unlock(&rnp->exp_funnel_mutex);
+		else if (rdp)
+			mutex_unlock(&rdp->exp_funnel_mutex);
+		/* Ensure test happens before caller kfree(). */
+		smp_mb__before_atomic(); /* ^^^ */
+		atomic_long_inc(stat);
+		return true;
+	}
+	return false;
+}
+
+/*
+ * Funnel-lock acquisition for expedited grace periods.  Returns a
+ * pointer to the root rcu_node structure, or NULL if some other
+ * task did the expedited grace period for us.
+ */
+static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
+{
+	struct rcu_data *rdp;
+	struct rcu_node *rnp0;
+	struct rcu_node *rnp1 = NULL;
+
+	/*
+	 * First try directly acquiring the root lock in order to reduce
+	 * latency in the common case where expedited grace periods are
+	 * rare.  We check mutex_is_locked() to avoid pathological levels of
+	 * memory contention on ->exp_funnel_mutex in the heavy-load case.
+	 */
+	rnp0 = rcu_get_root(rsp);
+	if (!mutex_is_locked(&rnp0->exp_funnel_mutex)) {
+		if (mutex_trylock(&rnp0->exp_funnel_mutex)) {
+			if (sync_exp_work_done(rsp, rnp0, NULL,
+					       &rsp->expedited_workdone0, s))
+				return NULL;
+			return rnp0;
+		}
+	}
+
+	/*
+	 * Each pass through the following loop works its way
+	 * up the rcu_node tree, returning if others have done the
+	 * work or otherwise falls through holding the root rnp's
+	 * ->exp_funnel_mutex.  The mapping from CPU to rcu_node structure
+	 * can be inexact, as it is just promoting locality and is not
+	 * strictly needed for correctness.
+	 */
+	rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
+	if (sync_exp_work_done(rsp, NULL, NULL, &rsp->expedited_workdone1, s))
+		return NULL;
+	mutex_lock(&rdp->exp_funnel_mutex);
+	rnp0 = rdp->mynode;
+	for (; rnp0 != NULL; rnp0 = rnp0->parent) {
+		if (sync_exp_work_done(rsp, rnp1, rdp,
+				       &rsp->expedited_workdone2, s))
+			return NULL;
+		mutex_lock(&rnp0->exp_funnel_mutex);
+		if (rnp1)
+			mutex_unlock(&rnp1->exp_funnel_mutex);
+		else
+			mutex_unlock(&rdp->exp_funnel_mutex);
+		rnp1 = rnp0;
+	}
+	if (sync_exp_work_done(rsp, rnp1, rdp,
+			       &rsp->expedited_workdone3, s))
+		return NULL;
+	return rnp1;
+}
+
+/* Invoked on each online non-idle CPU for expedited quiescent state. */
+static int synchronize_sched_expedited_cpu_stop(void *data)
+{
+	struct rcu_data *rdp = data;
+	struct rcu_state *rsp = rdp->rsp;
+
+	/* We are here: If we are last, do the wakeup. */
+	rdp->exp_done = true;
+	if (atomic_dec_and_test(&rsp->expedited_need_qs))
+		wake_up(&rsp->expedited_wq);
 	return 0;
 }
 
+static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
+{
+	int cpu;
+	unsigned long jiffies_stall;
+	unsigned long jiffies_start;
+	struct rcu_data *rdp;
+	int ret;
+
+	jiffies_stall = rcu_jiffies_till_stall_check();
+	jiffies_start = jiffies;
+
+	for (;;) {
+		ret = wait_event_interruptible_timeout(
+				rsp->expedited_wq,
+				!atomic_read(&rsp->expedited_need_qs),
+				jiffies_stall);
+		if (ret > 0)
+			return;
+		if (ret < 0) {
+			/* Hit a signal, disable CPU stall warnings. */
+			wait_event(rsp->expedited_wq,
+				   !atomic_read(&rsp->expedited_need_qs));
+			return;
+		}
+		pr_err("INFO: %s detected expedited stalls on CPUs: {",
+		       rsp->name);
+		for_each_online_cpu(cpu) {
+			rdp = per_cpu_ptr(rsp->rda, cpu);
+
+			if (rdp->exp_done)
+				continue;
+			pr_cont(" %d", cpu);
+		}
+		pr_cont(" } %lu jiffies s: %lu\n",
+			jiffies - jiffies_start, rsp->expedited_sequence);
+		for_each_online_cpu(cpu) {
+			rdp = per_cpu_ptr(rsp->rda, cpu);
+
+			if (rdp->exp_done)
+				continue;
+			dump_cpu_task(cpu);
+		}
+		jiffies_stall = 3 * rcu_jiffies_till_stall_check() + 3;
+	}
+}
+
 /**
  * synchronize_sched_expedited - Brute-force RCU-sched grace period
  *
@@ -3281,58 +3524,21 @@ static int synchronize_sched_expedited_cpu_stop(void *data)
  * restructure your code to batch your updates, and then use a single
  * synchronize_sched() instead.
  *
- * This implementation can be thought of as an application of ticket
- * locking to RCU, with sync_sched_expedited_started and
- * sync_sched_expedited_done taking on the roles of the halves
- * of the ticket-lock word.  Each task atomically increments
- * sync_sched_expedited_started upon entry, snapshotting the old value,
- * then attempts to stop all the CPUs.  If this succeeds, then each
- * CPU will have executed a context switch, resulting in an RCU-sched
- * grace period.  We are then done, so we use atomic_cmpxchg() to
- * update sync_sched_expedited_done to match our snapshot -- but
- * only if someone else has not already advanced past our snapshot.
- *
- * On the other hand, if try_stop_cpus() fails, we check the value
- * of sync_sched_expedited_done.  If it has advanced past our
- * initial snapshot, then someone else must have forced a grace period
- * some time after we took our snapshot.  In this case, our work is
- * done for us, and we can simply return.  Otherwise, we try again,
- * but keep our initial snapshot for purposes of checking for someone
- * doing our work for us.
- *
- * If we fail too many times in a row, we fall back to synchronize_sched().
+ * This implementation can be thought of as an application of sequence
+ * locking to expedited grace periods, but using the sequence counter to
+ * determine when someone else has already done the work instead of for
+ * retrying readers.
  */
 void synchronize_sched_expedited(void)
 {
-	cpumask_var_t cm;
-	bool cma = false;
 	int cpu;
-	long firstsnap, s, snap;
-	int trycount = 0;
+	unsigned long s;
+	struct rcu_node *rnp;
 	struct rcu_state *rsp = &rcu_sched_state;
 
-	/*
-	 * If we are in danger of counter wrap, just do synchronize_sched().
-	 * By allowing sync_sched_expedited_started to advance no more than
-	 * ULONG_MAX/8 ahead of sync_sched_expedited_done, we are ensuring
-	 * that more than 3.5 billion CPUs would be required to force a
-	 * counter wrap on a 32-bit system.  Quite a few more CPUs would of
-	 * course be required on a 64-bit system.
-	 */
-	if (ULONG_CMP_GE((ulong)atomic_long_read(&rsp->expedited_start),
-			 (ulong)atomic_long_read(&rsp->expedited_done) +
-			 ULONG_MAX / 8)) {
-		wait_rcu_gp(call_rcu_sched);
-		atomic_long_inc(&rsp->expedited_wrap);
-		return;
-	}
+	/* Take a snapshot of the sequence number.  */
+	s = rcu_exp_gp_seq_snap(rsp);
 
-	/*
-	 * Take a ticket.  Note that atomic_inc_return() implies a
-	 * full memory barrier.
-	 */
-	snap = atomic_long_inc_return(&rsp->expedited_start);
-	firstsnap = snap;
 	if (!try_get_online_cpus()) {
 		/* CPU hotplug operation in flight, fall back to normal GP. */
 		wait_rcu_gp(call_rcu_sched);
@@ -3341,100 +3547,38 @@ void synchronize_sched_expedited(void)
 	}
 	WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id()));
 
-	/* Offline CPUs, idle CPUs, and any CPU we run on are quiescent. */
-	cma = zalloc_cpumask_var(&cm, GFP_KERNEL);
-	if (cma) {
-		cpumask_copy(cm, cpu_online_mask);
-		cpumask_clear_cpu(raw_smp_processor_id(), cm);
-		for_each_cpu(cpu, cm) {
-			struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
-
-			if (!(atomic_add_return(0, &rdtp->dynticks) & 0x1))
-				cpumask_clear_cpu(cpu, cm);
-		}
-		if (cpumask_weight(cm) == 0)
-			goto all_cpus_idle;
+	rnp = exp_funnel_lock(rsp, s);
+	if (rnp == NULL) {
+		put_online_cpus();
+		return;  /* Someone else did our work for us. */
 	}
 
-	/*
-	 * Each pass through the following loop attempts to force a
-	 * context switch on each CPU.
-	 */
-	while (try_stop_cpus(cma ? cm : cpu_online_mask,
-			     synchronize_sched_expedited_cpu_stop,
-			     NULL) == -EAGAIN) {
-		put_online_cpus();
-		atomic_long_inc(&rsp->expedited_tryfail);
-
-		/* Check to see if someone else did our work for us. */
-		s = atomic_long_read(&rsp->expedited_done);
-		if (ULONG_CMP_GE((ulong)s, (ulong)firstsnap)) {
-			/* ensure test happens before caller kfree */
-			smp_mb__before_atomic(); /* ^^^ */
-			atomic_long_inc(&rsp->expedited_workdone1);
-			free_cpumask_var(cm);
-			return;
-		}
+	rcu_exp_gp_seq_start(rsp);
 
-		/* No joy, try again later.  Or just synchronize_sched(). */
-		if (trycount++ < 10) {
-			udelay(trycount * num_online_cpus());
-		} else {
-			wait_rcu_gp(call_rcu_sched);
-			atomic_long_inc(&rsp->expedited_normal);
-			free_cpumask_var(cm);
-			return;
-		}
+	/* Stop each CPU that is online, non-idle, and not us. */
+	init_waitqueue_head(&rsp->expedited_wq);
+	atomic_set(&rsp->expedited_need_qs, 1); /* Extra count avoids race. */
+	for_each_online_cpu(cpu) {
+		struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+		struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
 
-		/* Recheck to see if someone else did our work for us. */
-		s = atomic_long_read(&rsp->expedited_done);
-		if (ULONG_CMP_GE((ulong)s, (ulong)firstsnap)) {
-			/* ensure test happens before caller kfree */
-			smp_mb__before_atomic(); /* ^^^ */
-			atomic_long_inc(&rsp->expedited_workdone2);
-			free_cpumask_var(cm);
-			return;
-		}
+		rdp->exp_done = false;
 
-		/*
-		 * Refetching sync_sched_expedited_started allows later
-		 * callers to piggyback on our grace period.  We retry
-		 * after they started, so our grace period works for them,
-		 * and they started after our first try, so their grace
-		 * period works for us.
-		 */
-		if (!try_get_online_cpus()) {
-			/* CPU hotplug operation in flight, use normal GP. */
-			wait_rcu_gp(call_rcu_sched);
-			atomic_long_inc(&rsp->expedited_normal);
-			free_cpumask_var(cm);
-			return;
-		}
-		snap = atomic_long_read(&rsp->expedited_start);
-		smp_mb(); /* ensure read is before try_stop_cpus(). */
+		/* Skip our CPU and any idle CPUs. */
+		if (raw_smp_processor_id() == cpu ||
+		    !(atomic_add_return(0, &rdtp->dynticks) & 0x1))
+			continue;
+		atomic_inc(&rsp->expedited_need_qs);
+		stop_one_cpu_nowait(cpu, synchronize_sched_expedited_cpu_stop,
+				    rdp, &rdp->exp_stop_work);
 	}
-	atomic_long_inc(&rsp->expedited_stoppedcpus);
 
-all_cpus_idle:
-	free_cpumask_var(cm);
+	/* Remove extra count and, if necessary, wait for CPUs to stop. */
+	if (!atomic_dec_and_test(&rsp->expedited_need_qs))
+		synchronize_sched_expedited_wait(rsp);
 
-	/*
-	 * Everyone up to our most recent fetch is covered by our grace
-	 * period.  Update the counter, but only if our work is still
-	 * relevant -- which it won't be if someone who started later
-	 * than we did already did their update.
-	 */
-	do {
-		atomic_long_inc(&rsp->expedited_done_tries);
-		s = atomic_long_read(&rsp->expedited_done);
-		if (ULONG_CMP_GE((ulong)s, (ulong)snap)) {
-			/* ensure test happens before caller kfree */
-			smp_mb__before_atomic(); /* ^^^ */
-			atomic_long_inc(&rsp->expedited_done_lost);
-			break;
-		}
-	} while (atomic_long_cmpxchg(&rsp->expedited_done, s, snap) != s);
-	atomic_long_inc(&rsp->expedited_done_exit);
+	rcu_exp_gp_seq_end(rsp);
+	mutex_unlock(&rnp->exp_funnel_mutex);
 
 	put_online_cpus();
 }
@@ -3571,10 +3715,10 @@ static void rcu_barrier_callback(struct rcu_head *rhp)
 	struct rcu_state *rsp = rdp->rsp;
 
 	if (atomic_dec_and_test(&rsp->barrier_cpu_count)) {
-		_rcu_barrier_trace(rsp, "LastCB", -1, rsp->n_barrier_done);
+		_rcu_barrier_trace(rsp, "LastCB", -1, rsp->barrier_sequence);
 		complete(&rsp->barrier_completion);
 	} else {
-		_rcu_barrier_trace(rsp, "CB", -1, rsp->n_barrier_done);
+		_rcu_barrier_trace(rsp, "CB", -1, rsp->barrier_sequence);
 	}
 }
 
@@ -3586,7 +3730,7 @@ static void rcu_barrier_func(void *type)
 	struct rcu_state *rsp = type;
 	struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
 
-	_rcu_barrier_trace(rsp, "IRQ", -1, rsp->n_barrier_done);
+	_rcu_barrier_trace(rsp, "IRQ", -1, rsp->barrier_sequence);
 	atomic_inc(&rsp->barrier_cpu_count);
 	rsp->call(&rdp->barrier_head, rcu_barrier_callback);
 }
@@ -3599,55 +3743,24 @@ static void _rcu_barrier(struct rcu_state *rsp)
 {
 	int cpu;
 	struct rcu_data *rdp;
-	unsigned long snap = READ_ONCE(rsp->n_barrier_done);
-	unsigned long snap_done;
+	unsigned long s = rcu_seq_snap(&rsp->barrier_sequence);
 
-	_rcu_barrier_trace(rsp, "Begin", -1, snap);
+	_rcu_barrier_trace(rsp, "Begin", -1, s);
 
 	/* Take mutex to serialize concurrent rcu_barrier() requests. */
 	mutex_lock(&rsp->barrier_mutex);
 
-	/*
-	 * Ensure that all prior references, including to ->n_barrier_done,
-	 * are ordered before the _rcu_barrier() machinery.
-	 */
-	smp_mb();  /* See above block comment. */
-
-	/*
-	 * Recheck ->n_barrier_done to see if others did our work for us.
-	 * This means checking ->n_barrier_done for an even-to-odd-to-even
-	 * transition.  The "if" expression below therefore rounds the old
-	 * value up to the next even number and adds two before comparing.
-	 */
-	snap_done = rsp->n_barrier_done;
-	_rcu_barrier_trace(rsp, "Check", -1, snap_done);
-
-	/*
-	 * If the value in snap is odd, we needed to wait for the current
-	 * rcu_barrier() to complete, then wait for the next one, in other
-	 * words, we need the value of snap_done to be three larger than
-	 * the value of snap.  On the other hand, if the value in snap is
-	 * even, we only had to wait for the next rcu_barrier() to complete,
-	 * in other words, we need the value of snap_done to be only two
-	 * greater than the value of snap.  The "(snap + 3) & ~0x1" computes
-	 * this for us (thank you, Linus!).
-	 */
-	if (ULONG_CMP_GE(snap_done, (snap + 3) & ~0x1)) {
-		_rcu_barrier_trace(rsp, "EarlyExit", -1, snap_done);
+	/* Did someone else do our work for us? */
+	if (rcu_seq_done(&rsp->barrier_sequence, s)) {
+		_rcu_barrier_trace(rsp, "EarlyExit", -1, rsp->barrier_sequence);
 		smp_mb(); /* caller's subsequent code after above check. */
 		mutex_unlock(&rsp->barrier_mutex);
 		return;
 	}
 
-	/*
-	 * Increment ->n_barrier_done to avoid duplicate work.  Use
-	 * WRITE_ONCE() to prevent the compiler from speculating
-	 * the increment to precede the early-exit check.
-	 */
-	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. */
+	/* Mark the start of the barrier operation. */
+	rcu_seq_start(&rsp->barrier_sequence);
+	_rcu_barrier_trace(rsp, "Inc1", -1, rsp->barrier_sequence);
 
 	/*
 	 * Initialize the count to one rather than to zero in order to
@@ -3671,10 +3784,10 @@ static void _rcu_barrier(struct rcu_state *rsp)
 		if (rcu_is_nocb_cpu(cpu)) {
 			if (!rcu_nocb_cpu_needs_barrier(rsp, cpu)) {
 				_rcu_barrier_trace(rsp, "OfflineNoCB", cpu,
-						   rsp->n_barrier_done);
+						   rsp->barrier_sequence);
 			} else {
 				_rcu_barrier_trace(rsp, "OnlineNoCB", cpu,
-						   rsp->n_barrier_done);
+						   rsp->barrier_sequence);
 				smp_mb__before_atomic();
 				atomic_inc(&rsp->barrier_cpu_count);
 				__call_rcu(&rdp->barrier_head,
@@ -3682,11 +3795,11 @@ static void _rcu_barrier(struct rcu_state *rsp)
 			}
 		} else if (READ_ONCE(rdp->qlen)) {
 			_rcu_barrier_trace(rsp, "OnlineQ", cpu,
-					   rsp->n_barrier_done);
+					   rsp->barrier_sequence);
 			smp_call_function_single(cpu, rcu_barrier_func, rsp, 1);
 		} else {
 			_rcu_barrier_trace(rsp, "OnlineNQ", cpu,
-					   rsp->n_barrier_done);
+					   rsp->barrier_sequence);
 		}
 	}
 	put_online_cpus();
@@ -3698,16 +3811,13 @@ static void _rcu_barrier(struct rcu_state *rsp)
 	if (atomic_dec_and_test(&rsp->barrier_cpu_count))
 		complete(&rsp->barrier_completion);
 
-	/* Increment ->n_barrier_done to prevent duplicate work. */
-	smp_mb(); /* Keep increment after above mechanism. */
-	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. */
-
 	/* Wait for all rcu_barrier_callback() callbacks to be invoked. */
 	wait_for_completion(&rsp->barrier_completion);
 
+	/* Mark the end of the barrier operation. */
+	_rcu_barrier_trace(rsp, "Inc2", -1, rsp->barrier_sequence);
+	rcu_seq_end(&rsp->barrier_sequence);
+
 	/* Other rcu_barrier() invocations can now safely proceed. */
 	mutex_unlock(&rsp->barrier_mutex);
 }
@@ -3770,6 +3880,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 	WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1);
 	rdp->cpu = cpu;
 	rdp->rsp = rsp;
+	mutex_init(&rdp->exp_funnel_mutex);
 	rcu_boot_init_nocb_percpu_data(rdp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
@@ -3961,22 +4072,22 @@ void rcu_scheduler_starting(void)
  * Compute the per-level fanout, either using the exact fanout specified
  * or balancing the tree, depending on the rcu_fanout_exact boot parameter.
  */
-static void __init rcu_init_levelspread(struct rcu_state *rsp)
+static void __init rcu_init_levelspread(int *levelspread, const int *levelcnt)
 {
 	int i;
 
 	if (rcu_fanout_exact) {
-		rsp->levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
+		levelspread[rcu_num_lvls - 1] = rcu_fanout_leaf;
 		for (i = rcu_num_lvls - 2; i >= 0; i--)
-			rsp->levelspread[i] = RCU_FANOUT;
+			levelspread[i] = RCU_FANOUT;
 	} else {
 		int ccur;
 		int cprv;
 
 		cprv = nr_cpu_ids;
 		for (i = rcu_num_lvls - 1; i >= 0; i--) {
-			ccur = rsp->levelcnt[i];
-			rsp->levelspread[i] = (cprv + ccur - 1) / ccur;
+			ccur = levelcnt[i];
+			levelspread[i] = (cprv + ccur - 1) / ccur;
 			cprv = ccur;
 		}
 	}
@@ -3988,23 +4099,20 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp)
 static void __init rcu_init_one(struct rcu_state *rsp,
 		struct rcu_data __percpu *rda)
 {
-	static const char * const buf[] = {
-		"rcu_node_0",
-		"rcu_node_1",
-		"rcu_node_2",
-		"rcu_node_3" };  /* Match MAX_RCU_LVLS */
-	static const char * const fqs[] = {
-		"rcu_node_fqs_0",
-		"rcu_node_fqs_1",
-		"rcu_node_fqs_2",
-		"rcu_node_fqs_3" };  /* Match MAX_RCU_LVLS */
+	static const char * const buf[] = RCU_NODE_NAME_INIT;
+	static const char * const fqs[] = RCU_FQS_NAME_INIT;
+	static const char * const exp[] = RCU_EXP_NAME_INIT;
+	static const char * const exp_sched[] = RCU_EXP_SCHED_NAME_INIT;
 	static u8 fl_mask = 0x1;
+
+	int levelcnt[RCU_NUM_LVLS];		/* # nodes in each level. */
+	int levelspread[RCU_NUM_LVLS];		/* kids/node in each level. */
 	int cpustride = 1;
 	int i;
 	int j;
 	struct rcu_node *rnp;
 
-	BUILD_BUG_ON(MAX_RCU_LVLS > ARRAY_SIZE(buf));  /* Fix buf[] init! */
+	BUILD_BUG_ON(RCU_NUM_LVLS > ARRAY_SIZE(buf));  /* Fix buf[] init! */
 
 	/* Silence gcc 4.8 false positive about array index out of range. */
 	if (rcu_num_lvls <= 0 || rcu_num_lvls > RCU_NUM_LVLS)
@@ -4013,19 +4121,19 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 	/* Initialize the level-tracking arrays. */
 
 	for (i = 0; i < rcu_num_lvls; i++)
-		rsp->levelcnt[i] = num_rcu_lvl[i];
+		levelcnt[i] = num_rcu_lvl[i];
 	for (i = 1; i < rcu_num_lvls; i++)
-		rsp->level[i] = rsp->level[i - 1] + rsp->levelcnt[i - 1];
-	rcu_init_levelspread(rsp);
+		rsp->level[i] = rsp->level[i - 1] + levelcnt[i - 1];
+	rcu_init_levelspread(levelspread, levelcnt);
 	rsp->flavor_mask = fl_mask;
 	fl_mask <<= 1;
 
 	/* Initialize the elements themselves, starting from the leaves. */
 
 	for (i = rcu_num_lvls - 1; i >= 0; i--) {
-		cpustride *= rsp->levelspread[i];
+		cpustride *= levelspread[i];
 		rnp = rsp->level[i];
-		for (j = 0; j < rsp->levelcnt[i]; j++, rnp++) {
+		for (j = 0; j < levelcnt[i]; j++, rnp++) {
 			raw_spin_lock_init(&rnp->lock);
 			lockdep_set_class_and_name(&rnp->lock,
 						   &rcu_node_class[i], buf[i]);
@@ -4045,14 +4153,23 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 				rnp->grpmask = 0;
 				rnp->parent = NULL;
 			} else {
-				rnp->grpnum = j % rsp->levelspread[i - 1];
+				rnp->grpnum = j % levelspread[i - 1];
 				rnp->grpmask = 1UL << rnp->grpnum;
 				rnp->parent = rsp->level[i - 1] +
-					      j / rsp->levelspread[i - 1];
+					      j / levelspread[i - 1];
 			}
 			rnp->level = i;
 			INIT_LIST_HEAD(&rnp->blkd_tasks);
 			rcu_init_one_nocb(rnp);
+			mutex_init(&rnp->exp_funnel_mutex);
+			if (rsp == &rcu_sched_state)
+				lockdep_set_class_and_name(
+					&rnp->exp_funnel_mutex,
+					&rcu_exp_sched_class[i], exp_sched[i]);
+			else
+				lockdep_set_class_and_name(
+					&rnp->exp_funnel_mutex,
+					&rcu_exp_class[i], exp[i]);
 		}
 	}
 
@@ -4076,9 +4193,7 @@ static void __init rcu_init_geometry(void)
 {
 	ulong d;
 	int i;
-	int j;
-	int n = nr_cpu_ids;
-	int rcu_capacity[MAX_RCU_LVLS + 1];
+	int rcu_capacity[RCU_NUM_LVLS];
 
 	/*
 	 * Initialize any unspecified boot parameters.
@@ -4101,47 +4216,49 @@ static void __init rcu_init_geometry(void)
 		rcu_fanout_leaf, nr_cpu_ids);
 
 	/*
-	 * Compute number of nodes that can be handled an rcu_node tree
-	 * with the given number of levels.  Setting rcu_capacity[0] makes
-	 * some of the arithmetic easier.
-	 */
-	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] * RCU_FANOUT;
-
-	/*
 	 * The boot-time rcu_fanout_leaf parameter is only permitted
 	 * to increase the leaf-level fanout, not decrease it.  Of course,
 	 * the leaf-level fanout cannot exceed the number of bits in
-	 * the rcu_node masks.  Finally, the tree must be able to accommodate
-	 * the configured number of CPUs.  Complain and fall back to the
-	 * compile-time values if these limits are exceeded.
+	 * the rcu_node masks.  Complain and fall back to the compile-
+	 * time values if these limits are exceeded.
 	 */
 	if (rcu_fanout_leaf < RCU_FANOUT_LEAF ||
-	    rcu_fanout_leaf > sizeof(unsigned long) * 8 ||
-	    n > rcu_capacity[MAX_RCU_LVLS]) {
+	    rcu_fanout_leaf > sizeof(unsigned long) * 8) {
+		rcu_fanout_leaf = RCU_FANOUT_LEAF;
 		WARN_ON(1);
 		return;
 	}
 
+	/*
+	 * Compute number of nodes that can be handled an rcu_node tree
+	 * with the given number of levels.
+	 */
+	rcu_capacity[0] = rcu_fanout_leaf;
+	for (i = 1; i < RCU_NUM_LVLS; i++)
+		rcu_capacity[i] = rcu_capacity[i - 1] * RCU_FANOUT;
+
+	/*
+	 * The tree must be able to accommodate the configured number of CPUs.
+	 * If this limit is exceeded than we have a serious problem elsewhere.
+	 */
+	if (nr_cpu_ids > rcu_capacity[RCU_NUM_LVLS - 1])
+		panic("rcu_init_geometry: rcu_capacity[] is too small");
+
+	/* Calculate the number of levels in the tree. */
+	for (i = 0; nr_cpu_ids > rcu_capacity[i]; i++) {
+	}
+	rcu_num_lvls = i + 1;
+
 	/* Calculate the number of rcu_nodes at each level of the tree. */
-	for (i = 1; i <= MAX_RCU_LVLS; i++)
-		if (n <= rcu_capacity[i]) {
-			for (j = 0; j <= i; j++)
-				num_rcu_lvl[j] =
-					DIV_ROUND_UP(n, rcu_capacity[i - j]);
-			rcu_num_lvls = i;
-			for (j = i + 1; j <= MAX_RCU_LVLS; j++)
-				num_rcu_lvl[j] = 0;
-			break;
-		}
+	for (i = 0; i < rcu_num_lvls; i++) {
+		int cap = rcu_capacity[(rcu_num_lvls - 1) - i];
+		num_rcu_lvl[i] = DIV_ROUND_UP(nr_cpu_ids, cap);
+	}
 
 	/* Calculate the total number of rcu_node structures. */
 	rcu_num_nodes = 0;
-	for (i = 0; i <= MAX_RCU_LVLS; i++)
+	for (i = 0; i < rcu_num_lvls; i++)
 		rcu_num_nodes += num_rcu_lvl[i];
-	rcu_num_nodes -= n;
 }
 
 /*
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 4adb7ca0bf47..2e991f8361e4 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -27,6 +27,7 @@
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/seqlock.h>
+#include <linux/stop_machine.h>
 
 /*
  * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and
@@ -36,8 +37,6 @@
  * Of course, your mileage may vary.
  */
 
-#define MAX_RCU_LVLS 4
-
 #ifdef CONFIG_RCU_FANOUT
 #define RCU_FANOUT CONFIG_RCU_FANOUT
 #else /* #ifdef CONFIG_RCU_FANOUT */
@@ -66,38 +65,53 @@
 #if NR_CPUS <= RCU_FANOUT_1
 #  define RCU_NUM_LVLS	      1
 #  define NUM_RCU_LVL_0	      1
-#  define NUM_RCU_LVL_1	      (NR_CPUS)
-#  define NUM_RCU_LVL_2	      0
-#  define NUM_RCU_LVL_3	      0
-#  define NUM_RCU_LVL_4	      0
+#  define NUM_RCU_NODES	      NUM_RCU_LVL_0
+#  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0 }
+#  define RCU_NODE_NAME_INIT  { "rcu_node_0" }
+#  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0" }
+#  define RCU_EXP_NAME_INIT   { "rcu_node_exp_0" }
+#  define RCU_EXP_SCHED_NAME_INIT \
+			      { "rcu_node_exp_sched_0" }
 #elif NR_CPUS <= RCU_FANOUT_2
 #  define RCU_NUM_LVLS	      2
 #  define NUM_RCU_LVL_0	      1
 #  define NUM_RCU_LVL_1	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
-#  define NUM_RCU_LVL_2	      (NR_CPUS)
-#  define NUM_RCU_LVL_3	      0
-#  define NUM_RCU_LVL_4	      0
+#  define NUM_RCU_NODES	      (NUM_RCU_LVL_0 + NUM_RCU_LVL_1)
+#  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0, NUM_RCU_LVL_1 }
+#  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1" }
+#  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1" }
+#  define RCU_EXP_NAME_INIT   { "rcu_node_exp_0", "rcu_node_exp_1" }
+#  define RCU_EXP_SCHED_NAME_INIT \
+			      { "rcu_node_exp_sched_0", "rcu_node_exp_sched_1" }
 #elif NR_CPUS <= RCU_FANOUT_3
 #  define RCU_NUM_LVLS	      3
 #  define NUM_RCU_LVL_0	      1
 #  define NUM_RCU_LVL_1	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
 #  define NUM_RCU_LVL_2	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
-#  define NUM_RCU_LVL_3	      (NR_CPUS)
-#  define NUM_RCU_LVL_4	      0
+#  define NUM_RCU_NODES	      (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2)
+#  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2 }
+#  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1", "rcu_node_2" }
+#  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2" }
+#  define RCU_EXP_NAME_INIT   { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2" }
+#  define RCU_EXP_SCHED_NAME_INIT \
+			      { "rcu_node_exp_sched_0", "rcu_node_exp_sched_1", "rcu_node_exp_sched_2" }
 #elif NR_CPUS <= RCU_FANOUT_4
 #  define RCU_NUM_LVLS	      4
 #  define NUM_RCU_LVL_0	      1
 #  define NUM_RCU_LVL_1	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_3)
 #  define NUM_RCU_LVL_2	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_2)
 #  define NUM_RCU_LVL_3	      DIV_ROUND_UP(NR_CPUS, RCU_FANOUT_1)
-#  define NUM_RCU_LVL_4	      (NR_CPUS)
+#  define NUM_RCU_NODES	      (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3)
+#  define NUM_RCU_LVL_INIT    { NUM_RCU_LVL_0, NUM_RCU_LVL_1, NUM_RCU_LVL_2, NUM_RCU_LVL_3 }
+#  define RCU_NODE_NAME_INIT  { "rcu_node_0", "rcu_node_1", "rcu_node_2", "rcu_node_3" }
+#  define RCU_FQS_NAME_INIT   { "rcu_node_fqs_0", "rcu_node_fqs_1", "rcu_node_fqs_2", "rcu_node_fqs_3" }
+#  define RCU_EXP_NAME_INIT   { "rcu_node_exp_0", "rcu_node_exp_1", "rcu_node_exp_2", "rcu_node_exp_3" }
+#  define RCU_EXP_SCHED_NAME_INIT \
+			      { "rcu_node_exp_sched_0", "rcu_node_exp_sched_1", "rcu_node_exp_sched_2", "rcu_node_exp_sched_3" }
 #else
 # error "CONFIG_RCU_FANOUT insufficient for NR_CPUS"
 #endif /* #if (NR_CPUS) <= RCU_FANOUT_1 */
 
-#define RCU_SUM (NUM_RCU_LVL_0 + NUM_RCU_LVL_1 + NUM_RCU_LVL_2 + NUM_RCU_LVL_3 + NUM_RCU_LVL_4)
-#define NUM_RCU_NODES (RCU_SUM - NR_CPUS)
-
 extern int rcu_num_lvls;
 extern int rcu_num_nodes;
 
@@ -236,6 +250,8 @@ struct rcu_node {
 	int need_future_gp[2];
 				/* Counts of upcoming no-CB GP requests. */
 	raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp;
+
+	struct mutex exp_funnel_mutex ____cacheline_internodealigned_in_smp;
 } ____cacheline_internodealigned_in_smp;
 
 /*
@@ -287,12 +303,13 @@ struct rcu_data {
 	bool		gpwrap;		/* Possible gpnum/completed wrap. */
 	struct rcu_node *mynode;	/* This CPU's leaf of hierarchy */
 	unsigned long grpmask;		/* Mask to apply to leaf qsmask. */
-#ifdef CONFIG_RCU_CPU_STALL_INFO
 	unsigned long	ticks_this_gp;	/* The number of scheduling-clock */
 					/*  ticks this CPU has handled */
 					/*  during and after the last grace */
 					/* period it is aware of. */
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_INFO */
+	struct cpu_stop_work exp_stop_work;
+					/* Expedited grace-period control */
+					/*  for CPU stopping. */
 
 	/* 2) batch handling */
 	/*
@@ -355,11 +372,13 @@ struct rcu_data {
 	unsigned long n_rp_nocb_defer_wakeup;
 	unsigned long n_rp_need_nothing;
 
-	/* 6) _rcu_barrier() and OOM callbacks. */
+	/* 6) _rcu_barrier(), OOM callbacks, and expediting. */
 	struct rcu_head barrier_head;
 #ifdef CONFIG_RCU_FAST_NO_HZ
 	struct rcu_head oom_head;
 #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
+	struct mutex exp_funnel_mutex;
+	bool exp_done;			/* Expedited QS for this CPU? */
 
 	/* 7) Callback offloading. */
 #ifdef CONFIG_RCU_NOCB_CPU
@@ -387,9 +406,7 @@ struct rcu_data {
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
 	/* 8) RCU CPU stall data. */
-#ifdef CONFIG_RCU_CPU_STALL_INFO
 	unsigned int softirq_snap;	/* Snapshot of softirq activity. */
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_INFO */
 
 	int cpu;
 	struct rcu_state *rsp;
@@ -442,9 +459,9 @@ do {									\
  */
 struct rcu_state {
 	struct rcu_node node[NUM_RCU_NODES];	/* Hierarchy. */
-	struct rcu_node *level[RCU_NUM_LVLS];	/* Hierarchy levels. */
-	u32 levelcnt[MAX_RCU_LVLS + 1];		/* # nodes in each level. */
-	u8 levelspread[RCU_NUM_LVLS];		/* kids/node in each level. */
+	struct rcu_node *level[RCU_NUM_LVLS + 1];
+						/* Hierarchy levels (+1 to */
+						/*  shut bogus gcc warning) */
 	u8 flavor_mask;				/* bit in flavor mask. */
 	struct rcu_data __percpu *rda;		/* pointer of percu rcu_data. */
 	void (*call)(struct rcu_head *head,	/* call_rcu() flavor. */
@@ -479,21 +496,18 @@ struct rcu_state {
 	struct mutex barrier_mutex;		/* Guards barrier fields. */
 	atomic_t barrier_cpu_count;		/* # CPUs waiting on. */
 	struct completion barrier_completion;	/* Wake at barrier end. */
-	unsigned long n_barrier_done;		/* ++ at start and end of */
+	unsigned long barrier_sequence;		/* ++ at start and end of */
 						/*  _rcu_barrier(). */
 	/* End of fields guarded by barrier_mutex. */
 
-	atomic_long_t expedited_start;		/* Starting ticket. */
-	atomic_long_t expedited_done;		/* Done ticket. */
-	atomic_long_t expedited_wrap;		/* # near-wrap incidents. */
-	atomic_long_t expedited_tryfail;	/* # acquisition failures. */
+	unsigned long expedited_sequence;	/* Take a ticket. */
+	atomic_long_t expedited_workdone0;	/* # done by others #0. */
 	atomic_long_t expedited_workdone1;	/* # done by others #1. */
 	atomic_long_t expedited_workdone2;	/* # done by others #2. */
+	atomic_long_t expedited_workdone3;	/* # done by others #3. */
 	atomic_long_t expedited_normal;		/* # fallbacks to normal. */
-	atomic_long_t expedited_stoppedcpus;	/* # successful stop_cpus. */
-	atomic_long_t expedited_done_tries;	/* # tries to update _done. */
-	atomic_long_t expedited_done_lost;	/* # times beaten to _done. */
-	atomic_long_t expedited_done_exit;	/* # times exited _done loop. */
+	atomic_t expedited_need_qs;		/* # CPUs left to check in. */
+	wait_queue_head_t expedited_wq;		/* Wait for check-ins. */
 
 	unsigned long jiffies_force_qs;		/* Time at which to invoke */
 						/*  force_quiescent_state(). */
@@ -527,7 +541,11 @@ struct rcu_state {
 /* Values for rcu_state structure's gp_flags field. */
 #define RCU_GP_WAIT_INIT 0	/* Initial state. */
 #define RCU_GP_WAIT_GPS  1	/* Wait for grace-period start. */
-#define RCU_GP_WAIT_FQS  2	/* Wait for force-quiescent-state time. */
+#define RCU_GP_DONE_GPS  2	/* Wait done for grace-period start. */
+#define RCU_GP_WAIT_FQS  3	/* Wait for force-quiescent-state time. */
+#define RCU_GP_DOING_FQS 4	/* Wait done for force-quiescent-state time. */
+#define RCU_GP_CLEANUP   5	/* Grace-period cleanup started. */
+#define RCU_GP_CLEANED   6	/* Grace-period cleanup complete. */
 
 extern struct list_head rcu_struct_flavors;
 
@@ -635,3 +653,15 @@ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
 #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
 }
 #endif /* #ifdef CONFIG_RCU_TRACE */
+
+/*
+ * Place this after a lock-acquisition primitive to guarantee that
+ * an UNLOCK+LOCK pair act as a full barrier.  This guarantee applies
+ * if the UNLOCK and LOCK are executed by the same CPU or if the
+ * UNLOCK and LOCK operate on the same lock variable.
+ */
+#ifdef CONFIG_PPC
+#define smp_mb__after_unlock_lock()	smp_mb()  /* Full ordering for lock. */
+#else /* #ifdef CONFIG_PPC */
+#define smp_mb__after_unlock_lock()	do { } while (0)
+#endif /* #else #ifdef CONFIG_PPC */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 013485fb2b06..b2bf3963a0ae 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -82,10 +82,8 @@ static void __init rcu_bootup_announce_oddness(void)
 		pr_info("\tRCU lockdep checking is enabled.\n");
 	if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST_RUNNABLE))
 		pr_info("\tRCU torture testing starts during boot.\n");
-	if (IS_ENABLED(CONFIG_RCU_CPU_STALL_INFO))
-		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 (RCU_NUM_LVLS >= 4)
+		pr_info("\tFour(or more)-level hierarchy is enabled.\n");
 	if (RCU_FANOUT_LEAF != 16)
 		pr_info("\tBuild-time adjustment of leaf fanout to %d.\n",
 			RCU_FANOUT_LEAF);
@@ -418,8 +416,6 @@ static void rcu_print_detail_task_stall(struct rcu_state *rsp)
 		rcu_print_detail_task_stall_rnp(rnp);
 }
 
-#ifdef CONFIG_RCU_CPU_STALL_INFO
-
 static void rcu_print_task_stall_begin(struct rcu_node *rnp)
 {
 	pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):",
@@ -431,18 +427,6 @@ static void rcu_print_task_stall_end(void)
 	pr_cont("\n");
 }
 
-#else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */
-
-static void rcu_print_task_stall_begin(struct rcu_node *rnp)
-{
-}
-
-static void rcu_print_task_stall_end(void)
-{
-}
-
-#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_INFO */
-
 /*
  * Scan the current list of tasks blocked within RCU read-side critical
  * sections, printing out the tid of each.
@@ -538,10 +522,10 @@ EXPORT_SYMBOL_GPL(call_rcu);
  */
 void synchronize_rcu(void)
 {
-	rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) &&
-			   !lock_is_held(&rcu_lock_map) &&
-			   !lock_is_held(&rcu_sched_lock_map),
-			   "Illegal synchronize_rcu() in RCU read-side critical section");
+	RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
+			 lock_is_held(&rcu_lock_map) ||
+			 lock_is_held(&rcu_sched_lock_map),
+			 "Illegal synchronize_rcu() in RCU read-side critical section");
 	if (!rcu_scheduler_active)
 		return;
 	if (rcu_gp_is_expedited())
@@ -552,8 +536,6 @@ void synchronize_rcu(void)
 EXPORT_SYMBOL_GPL(synchronize_rcu);
 
 static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq);
-static unsigned long sync_rcu_preempt_exp_count;
-static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex);
 
 /*
  * Return non-zero if there are any tasks in RCU read-side critical
@@ -573,7 +555,7 @@ static int rcu_preempted_readers_exp(struct rcu_node *rnp)
  * for the current expedited grace period.  Works only for preemptible
  * RCU -- other RCU implementation use other means.
  *
- * Caller must hold sync_rcu_preempt_exp_mutex.
+ * Caller must hold the root rcu_node's exp_funnel_mutex.
  */
 static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
 {
@@ -589,7 +571,7 @@ static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
  * recursively up the tree.  (Calm down, calm down, we do the recursion
  * iteratively!)
  *
- * Caller must hold sync_rcu_preempt_exp_mutex.
+ * Caller must hold the root rcu_node's exp_funnel_mutex.
  */
 static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 			       bool wake)
@@ -628,7 +610,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
  * set the ->expmask bits on the leaf rcu_node structures to tell phase 2
  * that work is needed here.
  *
- * Caller must hold sync_rcu_preempt_exp_mutex.
+ * Caller must hold the root rcu_node's exp_funnel_mutex.
  */
 static void
 sync_rcu_preempt_exp_init1(struct rcu_state *rsp, struct rcu_node *rnp)
@@ -671,7 +653,7 @@ sync_rcu_preempt_exp_init1(struct rcu_state *rsp, struct rcu_node *rnp)
  * invoke rcu_report_exp_rnp() to clear out the upper-level ->expmask bits,
  * enabling rcu_read_unlock_special() to do the bit-clearing.
  *
- * Caller must hold sync_rcu_preempt_exp_mutex.
+ * Caller must hold the root rcu_node's exp_funnel_mutex.
  */
 static void
 sync_rcu_preempt_exp_init2(struct rcu_state *rsp, struct rcu_node *rnp)
@@ -719,51 +701,17 @@ sync_rcu_preempt_exp_init2(struct rcu_state *rsp, struct rcu_node *rnp)
 void synchronize_rcu_expedited(void)
 {
 	struct rcu_node *rnp;
+	struct rcu_node *rnp_unlock;
 	struct rcu_state *rsp = rcu_state_p;
-	unsigned long snap;
-	int trycount = 0;
+	unsigned long s;
 
-	smp_mb(); /* Caller's modifications seen first by other CPUs. */
-	snap = READ_ONCE(sync_rcu_preempt_exp_count) + 1;
-	smp_mb(); /* Above access cannot bleed into critical section. */
+	s = rcu_exp_gp_seq_snap(rsp);
 
-	/*
-	 * Block CPU-hotplug operations.  This means that any CPU-hotplug
-	 * operation that finds an rcu_node structure with tasks in the
-	 * process of being boosted will know that all tasks blocking
-	 * this expedited grace period will already be in the process of
-	 * being boosted.  This simplifies the process of moving tasks
-	 * from leaf to root rcu_node structures.
-	 */
-	if (!try_get_online_cpus()) {
-		/* CPU-hotplug operation in flight, fall back to normal GP. */
-		wait_rcu_gp(call_rcu);
-		return;
-	}
+	rnp_unlock = exp_funnel_lock(rsp, s);
+	if (rnp_unlock == NULL)
+		return;  /* Someone else did our work for us. */
 
-	/*
-	 * Acquire lock, falling back to synchronize_rcu() if too many
-	 * lock-acquisition failures.  Of course, if someone does the
-	 * expedited grace period for us, just leave.
-	 */
-	while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) {
-		if (ULONG_CMP_LT(snap,
-		    READ_ONCE(sync_rcu_preempt_exp_count))) {
-			put_online_cpus();
-			goto mb_ret; /* Others did our work for us. */
-		}
-		if (trycount++ < 10) {
-			udelay(trycount * num_online_cpus());
-		} else {
-			put_online_cpus();
-			wait_rcu_gp(call_rcu);
-			return;
-		}
-	}
-	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. */
-	}
+	rcu_exp_gp_seq_start(rsp);
 
 	/* force all RCU readers onto ->blkd_tasks lists. */
 	synchronize_sched_expedited();
@@ -779,20 +727,14 @@ void synchronize_rcu_expedited(void)
 	rcu_for_each_leaf_node(rsp, rnp)
 		sync_rcu_preempt_exp_init2(rsp, rnp);
 
-	put_online_cpus();
-
 	/* Wait for snapshotted ->blkd_tasks lists to drain. */
 	rnp = rcu_get_root(rsp);
 	wait_event(sync_rcu_preempt_exp_wq,
 		   sync_rcu_preempt_exp_done(rnp));
 
 	/* Clean up and exit. */
-	smp_mb(); /* ensure expedited GP seen before counter increment. */
-	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:
-	smp_mb(); /* ensure subsequent action seen after grace period. */
+	rcu_exp_gp_seq_end(rsp);
+	mutex_unlock(&rnp_unlock->exp_funnel_mutex);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
 
@@ -1061,8 +1003,7 @@ static int rcu_boost(struct rcu_node *rnp)
 }
 
 /*
- * Priority-boosting kthread.  One per leaf rcu_node and one for the
- * root rcu_node.
+ * Priority-boosting kthread, one per leaf rcu_node.
  */
 static int rcu_boost_kthread(void *arg)
 {
@@ -1680,12 +1621,10 @@ static int rcu_oom_notify(struct notifier_block *self,
 	 */
 	atomic_set(&oom_callback_count, 1);
 
-	get_online_cpus();
 	for_each_online_cpu(cpu) {
 		smp_call_function_single(cpu, rcu_oom_notify_cpu, NULL, 1);
 		cond_resched_rcu_qs();
 	}
-	put_online_cpus();
 
 	/* Unconditionally decrement: no need to wake ourselves up. */
 	atomic_dec(&oom_callback_count);
@@ -1706,8 +1645,6 @@ early_initcall(rcu_register_oom_notifier);
 
 #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
 
-#ifdef CONFIG_RCU_CPU_STALL_INFO
-
 #ifdef CONFIG_RCU_FAST_NO_HZ
 
 static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
@@ -1796,33 +1733,6 @@ static void increment_cpu_stall_ticks(void)
 		raw_cpu_inc(rsp->rda->ticks_this_gp);
 }
 
-#else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */
-
-static void print_cpu_stall_info_begin(void)
-{
-	pr_cont(" {");
-}
-
-static void print_cpu_stall_info(struct rcu_state *rsp, int cpu)
-{
-	pr_cont(" %d", cpu);
-}
-
-static void print_cpu_stall_info_end(void)
-{
-	pr_cont("} ");
-}
-
-static void zero_cpu_stall_ticks(struct rcu_data *rdp)
-{
-}
-
-static void increment_cpu_stall_ticks(void)
-{
-}
-
-#endif /* #else #ifdef CONFIG_RCU_CPU_STALL_INFO */
-
 #ifdef CONFIG_RCU_NOCB_CPU
 
 /*
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index 3ea7ffc7d5c4..6fc4c5ff3bb5 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -81,9 +81,9 @@ static void r_stop(struct seq_file *m, void *v)
 static int show_rcubarrier(struct seq_file *m, void *v)
 {
 	struct rcu_state *rsp = (struct rcu_state *)m->private;
-	seq_printf(m, "bcc: %d nbd: %lu\n",
+	seq_printf(m, "bcc: %d bseq: %lu\n",
 		   atomic_read(&rsp->barrier_cpu_count),
-		   rsp->n_barrier_done);
+		   rsp->barrier_sequence);
 	return 0;
 }
 
@@ -185,18 +185,15 @@ static int show_rcuexp(struct seq_file *m, void *v)
 {
 	struct rcu_state *rsp = (struct rcu_state *)m->private;
 
-	seq_printf(m, "s=%lu d=%lu w=%lu tf=%lu wd1=%lu wd2=%lu n=%lu sc=%lu dt=%lu dl=%lu dx=%lu\n",
-		   atomic_long_read(&rsp->expedited_start),
-		   atomic_long_read(&rsp->expedited_done),
-		   atomic_long_read(&rsp->expedited_wrap),
-		   atomic_long_read(&rsp->expedited_tryfail),
+	seq_printf(m, "s=%lu wd0=%lu wd1=%lu wd2=%lu wd3=%lu n=%lu enq=%d sc=%lu\n",
+		   rsp->expedited_sequence,
+		   atomic_long_read(&rsp->expedited_workdone0),
 		   atomic_long_read(&rsp->expedited_workdone1),
 		   atomic_long_read(&rsp->expedited_workdone2),
+		   atomic_long_read(&rsp->expedited_workdone3),
 		   atomic_long_read(&rsp->expedited_normal),
-		   atomic_long_read(&rsp->expedited_stoppedcpus),
-		   atomic_long_read(&rsp->expedited_done_tries),
-		   atomic_long_read(&rsp->expedited_done_lost),
-		   atomic_long_read(&rsp->expedited_done_exit));
+		   atomic_read(&rsp->expedited_need_qs),
+		   rsp->expedited_sequence / 2);
 	return 0;
 }
 
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index afaecb7a799a..7a0b3bc7c5ed 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -62,6 +62,55 @@ MODULE_ALIAS("rcupdate");
 
 module_param(rcu_expedited, int, 0);
 
+#if defined(CONFIG_DEBUG_LOCK_ALLOC) && defined(CONFIG_PREEMPT_COUNT)
+/**
+ * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
+ *
+ * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an
+ * RCU-sched read-side critical section.  In absence of
+ * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side
+ * critical section unless it can prove otherwise.  Note that disabling
+ * of preemption (including disabling irqs) counts as an RCU-sched
+ * read-side critical section.  This is useful for debug checks in functions
+ * that required that they be called within an RCU-sched read-side
+ * critical section.
+ *
+ * Check debug_lockdep_rcu_enabled() to prevent false positives during boot
+ * and while lockdep is disabled.
+ *
+ * Note that if the CPU is in the idle loop from an RCU point of
+ * view (ie: that we are in the section between rcu_idle_enter() and
+ * rcu_idle_exit()) then rcu_read_lock_held() returns false even if the CPU
+ * did an rcu_read_lock().  The reason for this is that RCU ignores CPUs
+ * that are in such a section, considering these as in extended quiescent
+ * state, so such a CPU is effectively never in an RCU read-side critical
+ * section regardless of what RCU primitives it invokes.  This state of
+ * affairs is required --- we need to keep an RCU-free window in idle
+ * where the CPU may possibly enter into low power mode. This way we can
+ * notice an extended quiescent state to other CPUs that started a grace
+ * period. Otherwise we would delay any grace period as long as we run in
+ * the idle task.
+ *
+ * Similarly, we avoid claiming an SRCU read lock held if the current
+ * CPU is offline.
+ */
+int rcu_read_lock_sched_held(void)
+{
+	int lockdep_opinion = 0;
+
+	if (!debug_lockdep_rcu_enabled())
+		return 1;
+	if (!rcu_is_watching())
+		return 0;
+	if (!rcu_lockdep_current_cpu_online())
+		return 0;
+	if (debug_locks)
+		lockdep_opinion = lock_is_held(&rcu_sched_lock_map);
+	return lockdep_opinion || preempt_count() != 0 || irqs_disabled();
+}
+EXPORT_SYMBOL(rcu_read_lock_sched_held);
+#endif
+
 #ifndef CONFIG_TINY_RCU
 
 static atomic_t rcu_expedited_nesting =
@@ -269,20 +318,37 @@ void wakeme_after_rcu(struct rcu_head *head)
 	rcu = container_of(head, struct rcu_synchronize, head);
 	complete(&rcu->completion);
 }
+EXPORT_SYMBOL_GPL(wakeme_after_rcu);
 
-void wait_rcu_gp(call_rcu_func_t crf)
+void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
+		   struct rcu_synchronize *rs_array)
 {
-	struct rcu_synchronize rcu;
+	int i;
 
-	init_rcu_head_on_stack(&rcu.head);
-	init_completion(&rcu.completion);
-	/* Will wake me after RCU finished. */
-	crf(&rcu.head, wakeme_after_rcu);
-	/* Wait for it. */
-	wait_for_completion(&rcu.completion);
-	destroy_rcu_head_on_stack(&rcu.head);
+	/* Initialize and register callbacks for each flavor specified. */
+	for (i = 0; i < n; i++) {
+		if (checktiny &&
+		    (crcu_array[i] == call_rcu ||
+		     crcu_array[i] == call_rcu_bh)) {
+			might_sleep();
+			continue;
+		}
+		init_rcu_head_on_stack(&rs_array[i].head);
+		init_completion(&rs_array[i].completion);
+		(crcu_array[i])(&rs_array[i].head, wakeme_after_rcu);
+	}
+
+	/* Wait for all callbacks to be invoked. */
+	for (i = 0; i < n; i++) {
+		if (checktiny &&
+		    (crcu_array[i] == call_rcu ||
+		     crcu_array[i] == call_rcu_bh))
+			continue;
+		wait_for_completion(&rs_array[i].completion);
+		destroy_rcu_head_on_stack(&rs_array[i].head);
+	}
 }
-EXPORT_SYMBOL_GPL(wait_rcu_gp);
+EXPORT_SYMBOL_GPL(__wait_rcu_gp);
 
 #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD
 void init_rcu_head(struct rcu_head *head)
@@ -523,8 +589,8 @@ EXPORT_SYMBOL_GPL(call_rcu_tasks);
 void synchronize_rcu_tasks(void)
 {
 	/* Complain if the scheduler has not started.  */
-	rcu_lockdep_assert(!rcu_scheduler_active,
-			   "synchronize_rcu_tasks called too soon");
+	RCU_LOCKDEP_WARN(!rcu_scheduler_active,
+			 "synchronize_rcu_tasks called too soon");
 
 	/* Wait for the grace period. */
 	wait_rcu_gp(call_rcu_tasks);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 78b4bad10081..5e73c79fadd0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2200,8 +2200,8 @@ unsigned long to_ratio(u64 period, u64 runtime)
 #ifdef CONFIG_SMP
 inline struct dl_bw *dl_bw_of(int i)
 {
-	rcu_lockdep_assert(rcu_read_lock_sched_held(),
-			   "sched RCU must be held");
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
+			 "sched RCU must be held");
 	return &cpu_rq(i)->rd->dl_bw;
 }
 
@@ -2210,8 +2210,8 @@ static inline int dl_bw_cpus(int i)
 	struct root_domain *rd = cpu_rq(i)->rd;
 	int cpus = 0;
 
-	rcu_lockdep_assert(rcu_read_lock_sched_held(),
-			   "sched RCU must be held");
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
+			 "sched RCU must be held");
 	for_each_cpu_and(i, rd->span, cpu_active_mask)
 		cpus++;
 
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 579ce1b929af..4008d9f95dd7 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -92,12 +92,10 @@ config NO_HZ_FULL
 	depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
 	# We need at least one periodic CPU for timekeeping
 	depends on SMP
-	# RCU_USER_QS dependency
 	depends on HAVE_CONTEXT_TRACKING
 	# VIRT_CPU_ACCOUNTING_GEN dependency
 	depends on HAVE_VIRT_CPU_ACCOUNTING_GEN
 	select NO_HZ_COMMON
-	select RCU_USER_QS
 	select RCU_NOCB_CPU
 	select VIRT_CPU_ACCOUNTING_GEN
 	select IRQ_WORK
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 4c4f06176f74..cb91c63b4f4a 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -338,20 +338,20 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq);
 #include <trace/events/workqueue.h>
 
 #define assert_rcu_or_pool_mutex()					\
-	rcu_lockdep_assert(rcu_read_lock_sched_held() ||		\
-			   lockdep_is_held(&wq_pool_mutex),		\
-			   "sched RCU or wq_pool_mutex should be held")
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() &&			\
+			 !lockdep_is_held(&wq_pool_mutex),		\
+			 "sched RCU or wq_pool_mutex should be held")
 
 #define assert_rcu_or_wq_mutex(wq)					\
-	rcu_lockdep_assert(rcu_read_lock_sched_held() ||		\
-			   lockdep_is_held(&wq->mutex),			\
-			   "sched RCU or wq->mutex should be held")
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() &&			\
+			 !lockdep_is_held(&wq->mutex),			\
+			 "sched RCU or wq->mutex should be held")
 
 #define assert_rcu_or_wq_mutex_or_pool_mutex(wq)			\
-	rcu_lockdep_assert(rcu_read_lock_sched_held() ||		\
-			   lockdep_is_held(&wq->mutex) ||		\
-			   lockdep_is_held(&wq_pool_mutex),		\
-			   "sched RCU, wq->mutex or wq_pool_mutex should be held")
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() &&			\
+			 !lockdep_is_held(&wq->mutex) &&		\
+			 !lockdep_is_held(&wq_pool_mutex),		\
+			 "sched RCU, wq->mutex or wq_pool_mutex should be held")
 
 #define for_each_cpu_worker_pool(pool, cpu)				\
 	for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0];		\