Merge branches 'fixes.2015.10.06a' and 'exp.2015.10.07a' into HEAD

exp.2015.10.07a:  Reduce OS jitter of RCU-sched expedited grace periods.
fixes.2015.10.06a:  Miscellaneous fixes.

4 files changed, 630 insertions, 310 deletions

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 4d296b0fb987..f07343b54fe5 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -71,7 +71,6 @@ 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
@@ -161,6 +160,8 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf);
 static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
 static void invoke_rcu_core(void);
 static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp);
+static void rcu_report_exp_rdp(struct rcu_state *rsp,
+			       struct rcu_data *rdp, bool wake);
 
 /* rcuc/rcub kthread realtime priority */
 #ifdef CONFIG_RCU_KTHREAD_PRIO
@@ -245,21 +246,33 @@ static int rcu_gp_in_progress(struct rcu_state *rsp)
  */
 void rcu_sched_qs(void)
 {
-	if (!__this_cpu_read(rcu_sched_data.passed_quiesce)) {
+	unsigned long flags;
+
+	if (__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) {
 		trace_rcu_grace_period(TPS("rcu_sched"),
 				       __this_cpu_read(rcu_sched_data.gpnum),
 				       TPS("cpuqs"));
-		__this_cpu_write(rcu_sched_data.passed_quiesce, 1);
+		__this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false);
+		if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))
+			return;
+		local_irq_save(flags);
+		if (__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) {
+			__this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, false);
+			rcu_report_exp_rdp(&rcu_sched_state,
+					   this_cpu_ptr(&rcu_sched_data),
+					   true);
+		}
+		local_irq_restore(flags);
 	}
 }
 
 void rcu_bh_qs(void)
 {
-	if (!__this_cpu_read(rcu_bh_data.passed_quiesce)) {
+	if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) {
 		trace_rcu_grace_period(TPS("rcu_bh"),
 				       __this_cpu_read(rcu_bh_data.gpnum),
 				       TPS("cpuqs"));
-		__this_cpu_write(rcu_bh_data.passed_quiesce, 1);
+		__this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false);
 	}
 }
 
@@ -1753,9 +1766,9 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 		 */
 		rdp->gpnum = rnp->gpnum;
 		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart"));
-		rdp->passed_quiesce = 0;
+		rdp->cpu_no_qs.b.norm = true;
 		rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
-		rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask);
+		rdp->core_needs_qs = !!(rnp->qsmask & rdp->grpmask);
 		zero_cpu_stall_ticks(rdp);
 		WRITE_ONCE(rdp->gpwrap, false);
 	}
@@ -2344,7 +2357,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 	rnp = rdp->mynode;
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	smp_mb__after_unlock_lock();
-	if ((rdp->passed_quiesce == 0 &&
+	if ((rdp->cpu_no_qs.b.norm &&
 	     rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) ||
 	    rdp->gpnum != rnp->gpnum || rnp->completed == rnp->gpnum ||
 	    rdp->gpwrap) {
@@ -2355,7 +2368,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 		 * We will instead need a new quiescent state that lies
 		 * within the current grace period.
 		 */
-		rdp->passed_quiesce = 0;	/* need qs for new gp. */
+		rdp->cpu_no_qs.b.norm = true;	/* need qs for new gp. */
 		rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_qs_ctr);
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
@@ -2364,7 +2377,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 	if ((rnp->qsmask & mask) == 0) {
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	} else {
-		rdp->qs_pending = 0;
+		rdp->core_needs_qs = 0;
 
 		/*
 		 * This GP can't end until cpu checks in, so all of our
@@ -2395,14 +2408,14 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
 	 * Does this CPU still need to do its part for current grace period?
 	 * If no, return and let the other CPUs do their part as well.
 	 */
-	if (!rdp->qs_pending)
+	if (!rdp->core_needs_qs)
 		return;
 
 	/*
 	 * Was there a quiescent state since the beginning of the grace
 	 * period? If no, then exit and wait for the next call.
 	 */
-	if (!rdp->passed_quiesce &&
+	if (rdp->cpu_no_qs.b.norm &&
 	    rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr))
 		return;
 
@@ -3386,6 +3399,191 @@ static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s)
 	return rcu_seq_done(&rsp->expedited_sequence, s);
 }
 
+/*
+ * Reset the ->expmaskinit values in the rcu_node tree to reflect any
+ * recent CPU-online activity.  Note that these masks are not cleared
+ * when CPUs go offline, so they reflect the union of all CPUs that have
+ * ever been online.  This means that this function normally takes its
+ * no-work-to-do fastpath.
+ */
+static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp)
+{
+	bool done;
+	unsigned long flags;
+	unsigned long mask;
+	unsigned long oldmask;
+	int ncpus = READ_ONCE(rsp->ncpus);
+	struct rcu_node *rnp;
+	struct rcu_node *rnp_up;
+
+	/* If no new CPUs onlined since last time, nothing to do. */
+	if (likely(ncpus == rsp->ncpus_snap))
+		return;
+	rsp->ncpus_snap = ncpus;
+
+	/*
+	 * Each pass through the following loop propagates newly onlined
+	 * CPUs for the current rcu_node structure up the rcu_node tree.
+	 */
+	rcu_for_each_leaf_node(rsp, rnp) {
+		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
+		if (rnp->expmaskinit == rnp->expmaskinitnext) {
+			raw_spin_unlock_irqrestore(&rnp->lock, flags);
+			continue;  /* No new CPUs, nothing to do. */
+		}
+
+		/* Update this node's mask, track old value for propagation. */
+		oldmask = rnp->expmaskinit;
+		rnp->expmaskinit = rnp->expmaskinitnext;
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+
+		/* If was already nonzero, nothing to propagate. */
+		if (oldmask)
+			continue;
+
+		/* Propagate the new CPU up the tree. */
+		mask = rnp->grpmask;
+		rnp_up = rnp->parent;
+		done = false;
+		while (rnp_up) {
+			raw_spin_lock_irqsave(&rnp_up->lock, flags);
+			smp_mb__after_unlock_lock();
+			if (rnp_up->expmaskinit)
+				done = true;
+			rnp_up->expmaskinit |= mask;
+			raw_spin_unlock_irqrestore(&rnp_up->lock, flags);
+			if (done)
+				break;
+			mask = rnp_up->grpmask;
+			rnp_up = rnp_up->parent;
+		}
+	}
+}
+
+/*
+ * Reset the ->expmask values in the rcu_node tree in preparation for
+ * a new expedited grace period.
+ */
+static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp)
+{
+	unsigned long flags;
+	struct rcu_node *rnp;
+
+	sync_exp_reset_tree_hotplug(rsp);
+	rcu_for_each_node_breadth_first(rsp, rnp) {
+		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
+		WARN_ON_ONCE(rnp->expmask);
+		rnp->expmask = rnp->expmaskinit;
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	}
+}
+
+/*
+ * Return non-zero if there is no RCU expedited grace period in progress
+ * for the specified rcu_node structure, in other words, if all CPUs and
+ * tasks covered by the specified rcu_node structure have done their bit
+ * for the current expedited grace period.  Works only for preemptible
+ * RCU -- other RCU implementation use other means.
+ *
+ * Caller must hold the root rcu_node's exp_funnel_mutex.
+ */
+static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
+{
+	return rnp->exp_tasks == NULL &&
+	       READ_ONCE(rnp->expmask) == 0;
+}
+
+/*
+ * Report the exit from RCU read-side critical section for the last task
+ * that queued itself during or before the current expedited preemptible-RCU
+ * grace period.  This event is reported either to the rcu_node structure on
+ * which the task was queued or to one of that rcu_node structure's ancestors,
+ * recursively up the tree.  (Calm down, calm down, we do the recursion
+ * iteratively!)
+ *
+ * Caller must hold the root rcu_node's exp_funnel_mutex and the
+ * specified rcu_node structure's ->lock.
+ */
+static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
+				 bool wake, unsigned long flags)
+	__releases(rnp->lock)
+{
+	unsigned long mask;
+
+	for (;;) {
+		if (!sync_rcu_preempt_exp_done(rnp)) {
+			if (!rnp->expmask)
+				rcu_initiate_boost(rnp, flags);
+			else
+				raw_spin_unlock_irqrestore(&rnp->lock, flags);
+			break;
+		}
+		if (rnp->parent == NULL) {
+			raw_spin_unlock_irqrestore(&rnp->lock, flags);
+			if (wake) {
+				smp_mb(); /* EGP done before wake_up(). */
+				wake_up(&rsp->expedited_wq);
+			}
+			break;
+		}
+		mask = rnp->grpmask;
+		raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
+		rnp = rnp->parent;
+		raw_spin_lock(&rnp->lock); /* irqs already disabled */
+		smp_mb__after_unlock_lock();
+		WARN_ON_ONCE(!(rnp->expmask & mask));
+		rnp->expmask &= ~mask;
+	}
+}
+
+/*
+ * Report expedited quiescent state for specified node.  This is a
+ * lock-acquisition wrapper function for __rcu_report_exp_rnp().
+ *
+ * Caller must hold the root rcu_node's exp_funnel_mutex.
+ */
+static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp,
+					      struct rcu_node *rnp, bool wake)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
+	__rcu_report_exp_rnp(rsp, rnp, wake, flags);
+}
+
+/*
+ * Report expedited quiescent state for multiple CPUs, all covered by the
+ * specified leaf rcu_node structure.  Caller must hold the root
+ * rcu_node's exp_funnel_mutex.
+ */
+static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp,
+				    unsigned long mask, bool wake)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
+	if (!(rnp->expmask & mask)) {
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		return;
+	}
+	rnp->expmask &= ~mask;
+	__rcu_report_exp_rnp(rsp, rnp, wake, flags); /* Releases rnp->lock. */
+}
+
+/*
+ * Report expedited quiescent state for specified rcu_data (CPU).
+ * Caller must hold the root rcu_node's exp_funnel_mutex.
+ */
+static void rcu_report_exp_rdp(struct rcu_state *rsp, struct rcu_data *rdp,
+			       bool wake)
+{
+	rcu_report_exp_cpu_mult(rsp, rdp->mynode, rdp->grpmask, wake);
+}
+
 /* 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,
@@ -3462,16 +3660,111 @@ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
 }
 
 /* Invoked on each online non-idle CPU for expedited quiescent state. */
-static int synchronize_sched_expedited_cpu_stop(void *data)
+static void sync_sched_exp_handler(void *data)
 {
-	struct rcu_data *rdp = data;
-	struct rcu_state *rsp = rdp->rsp;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
+	struct rcu_state *rsp = data;
 
-	/* 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;
+	rdp = this_cpu_ptr(rsp->rda);
+	rnp = rdp->mynode;
+	if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) ||
+	    __this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))
+		return;
+	__this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, true);
+	resched_cpu(smp_processor_id());
+}
+
+/* Send IPI for expedited cleanup if needed at end of CPU-hotplug operation. */
+static void sync_sched_exp_online_cleanup(int cpu)
+{
+	struct rcu_data *rdp;
+	int ret;
+	struct rcu_node *rnp;
+	struct rcu_state *rsp = &rcu_sched_state;
+
+	rdp = per_cpu_ptr(rsp->rda, cpu);
+	rnp = rdp->mynode;
+	if (!(READ_ONCE(rnp->expmask) & rdp->grpmask))
+		return;
+	ret = smp_call_function_single(cpu, sync_sched_exp_handler, rsp, 0);
+	WARN_ON_ONCE(ret);
+}
+
+/*
+ * Select the nodes that the upcoming expedited grace period needs
+ * to wait for.
+ */
+static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
+				     smp_call_func_t func)
+{
+	int cpu;
+	unsigned long flags;
+	unsigned long mask;
+	unsigned long mask_ofl_test;
+	unsigned long mask_ofl_ipi;
+	int ret;
+	struct rcu_node *rnp;
+
+	sync_exp_reset_tree(rsp);
+	rcu_for_each_leaf_node(rsp, rnp) {
+		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
+
+		/* Each pass checks a CPU for identity, offline, and idle. */
+		mask_ofl_test = 0;
+		for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) {
+			struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+			struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
+
+			if (raw_smp_processor_id() == cpu ||
+			    !(atomic_add_return(0, &rdtp->dynticks) & 0x1))
+				mask_ofl_test |= rdp->grpmask;
+		}
+		mask_ofl_ipi = rnp->expmask & ~mask_ofl_test;
+
+		/*
+		 * Need to wait for any blocked tasks as well.  Note that
+		 * additional blocking tasks will also block the expedited
+		 * GP until such time as the ->expmask bits are cleared.
+		 */
+		if (rcu_preempt_has_tasks(rnp))
+			rnp->exp_tasks = rnp->blkd_tasks.next;
+		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+
+		/* IPI the remaining CPUs for expedited quiescent state. */
+		mask = 1;
+		for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) {
+			if (!(mask_ofl_ipi & mask))
+				continue;
+retry_ipi:
+			ret = smp_call_function_single(cpu, func, rsp, 0);
+			if (!ret) {
+				mask_ofl_ipi &= ~mask;
+			} else {
+				/* Failed, raced with offline. */
+				raw_spin_lock_irqsave(&rnp->lock, flags);
+				if (cpu_online(cpu) &&
+				    (rnp->expmask & mask)) {
+					raw_spin_unlock_irqrestore(&rnp->lock,
+								   flags);
+					schedule_timeout_uninterruptible(1);
+					if (cpu_online(cpu) &&
+					    (rnp->expmask & mask))
+						goto retry_ipi;
+					raw_spin_lock_irqsave(&rnp->lock,
+							      flags);
+				}
+				if (!(rnp->expmask & mask))
+					mask_ofl_ipi &= ~mask;
+				raw_spin_unlock_irqrestore(&rnp->lock, flags);
+			}
+		}
+		/* Report quiescent states for those that went offline. */
+		mask_ofl_test |= mask_ofl_ipi;
+		if (mask_ofl_test)
+			rcu_report_exp_cpu_mult(rsp, rnp, mask_ofl_test, false);
+	}
 }
 
 static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
@@ -3479,7 +3772,9 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 	int cpu;
 	unsigned long jiffies_stall;
 	unsigned long jiffies_start;
-	struct rcu_data *rdp;
+	unsigned long mask;
+	struct rcu_node *rnp;
+	struct rcu_node *rnp_root = rcu_get_root(rsp);
 	int ret;
 
 	jiffies_stall = rcu_jiffies_till_stall_check();
@@ -3488,33 +3783,43 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 	for (;;) {
 		ret = wait_event_interruptible_timeout(
 				rsp->expedited_wq,
-				!atomic_read(&rsp->expedited_need_qs),
+				sync_rcu_preempt_exp_done(rnp_root),
 				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));
+				   sync_rcu_preempt_exp_done(rnp_root));
 			return;
 		}
-		pr_err("INFO: %s detected expedited stalls on CPUs: {",
+		pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {",
 		       rsp->name);
-		for_each_online_cpu(cpu) {
-			rdp = per_cpu_ptr(rsp->rda, cpu);
-
-			if (rdp->exp_done)
-				continue;
-			pr_cont(" %d", cpu);
+		rcu_for_each_leaf_node(rsp, rnp) {
+			(void)rcu_print_task_exp_stall(rnp);
+			mask = 1;
+			for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) {
+				struct rcu_data *rdp;
+
+				if (!(rnp->expmask & mask))
+					continue;
+				rdp = per_cpu_ptr(rsp->rda, cpu);
+				pr_cont(" %d-%c%c%c", cpu,
+					"O."[cpu_online(cpu)],
+					"o."[!!(rdp->grpmask & rnp->expmaskinit)],
+					"N."[!!(rdp->grpmask & rnp->expmaskinitnext)]);
+			}
+			mask <<= 1;
 		}
 		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);
+		rcu_for_each_leaf_node(rsp, rnp) {
+			mask = 1;
+			for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) {
+				if (!(rnp->expmask & mask))
+					continue;
+				dump_cpu_task(cpu);
+			}
 		}
 		jiffies_stall = 3 * rcu_jiffies_till_stall_check() + 3;
 	}
@@ -3538,7 +3843,6 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
  */
 void synchronize_sched_expedited(void)
 {
-	int cpu;
 	unsigned long s;
 	struct rcu_node *rnp;
 	struct rcu_state *rsp = &rcu_sched_state;
@@ -3546,48 +3850,16 @@ void synchronize_sched_expedited(void)
 	/* Take a snapshot of the sequence number.  */
 	s = rcu_exp_gp_seq_snap(rsp);
 
-	if (!try_get_online_cpus()) {
-		/* CPU hotplug operation in flight, fall back to normal GP. */
-		wait_rcu_gp(call_rcu_sched);
-		atomic_long_inc(&rsp->expedited_normal);
-		return;
-	}
-	WARN_ON_ONCE(cpu_is_offline(raw_smp_processor_id()));
-
 	rnp = exp_funnel_lock(rsp, s);
-	if (rnp == NULL) {
-		put_online_cpus();
+	if (rnp == NULL)
 		return;  /* Someone else did our work for us. */
-	}
 
 	rcu_exp_gp_seq_start(rsp);
-
-	/* 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);
-
-		rdp->exp_done = false;
-
-		/* 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);
-	}
-
-	/* 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);
+	sync_rcu_exp_select_cpus(rsp, sync_sched_exp_handler);
+	synchronize_sched_expedited_wait(rsp);
 
 	rcu_exp_gp_seq_end(rsp);
 	mutex_unlock(&rnp->exp_funnel_mutex);
-
-	put_online_cpus();
 }
 EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
 
@@ -3613,11 +3885,11 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 
 	/* Is the RCU core waiting for a quiescent state from this CPU? */
 	if (rcu_scheduler_fully_active &&
-	    rdp->qs_pending && !rdp->passed_quiesce &&
+	    rdp->core_needs_qs && rdp->cpu_no_qs.b.norm &&
 	    rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) {
-		rdp->n_rp_qs_pending++;
-	} else if (rdp->qs_pending &&
-		   (rdp->passed_quiesce ||
+		rdp->n_rp_core_needs_qs++;
+	} else if (rdp->core_needs_qs &&
+		   (!rdp->cpu_no_qs.b.norm ||
 		    rdp->rcu_qs_ctr_snap != __this_cpu_read(rcu_qs_ctr))) {
 		rdp->n_rp_report_qs++;
 		return 1;
@@ -3875,7 +4147,6 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
 static void __init
 rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 {
-	static struct lock_class_key rcu_exp_sched_rdp_class;
 	unsigned long flags;
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rcu_get_root(rsp);
@@ -3891,10 +4162,6 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 	mutex_init(&rdp->exp_funnel_mutex);
 	rcu_boot_init_nocb_percpu_data(rdp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
-	if (rsp == &rcu_sched_state)
-		lockdep_set_class_and_name(&rdp->exp_funnel_mutex,
-					   &rcu_exp_sched_rdp_class,
-					   "rcu_data_exp_sched");
 }
 
 /*
@@ -3913,7 +4180,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 
 	/* Set up local state, ensuring consistent view of global state. */
 	raw_spin_lock_irqsave(&rnp->lock, flags);
-	rdp->beenonline = 1;	 /* We have now been online. */
 	rdp->qlen_last_fqs_check = 0;
 	rdp->n_force_qs_snap = rsp->n_force_qs;
 	rdp->blimit = blimit;
@@ -3935,11 +4201,15 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	raw_spin_lock(&rnp->lock);		/* irqs already disabled. */
 	smp_mb__after_unlock_lock();
 	rnp->qsmaskinitnext |= mask;
+	rnp->expmaskinitnext |= mask;
+	if (!rdp->beenonline)
+		WRITE_ONCE(rsp->ncpus, READ_ONCE(rsp->ncpus) + 1);
+	rdp->beenonline = true;	 /* We have now been online. */
 	rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
 	rdp->completed = rnp->completed;
-	rdp->passed_quiesce = false;
+	rdp->cpu_no_qs.b.norm = true;
 	rdp->rcu_qs_ctr_snap = per_cpu(rcu_qs_ctr, cpu);
-	rdp->qs_pending = false;
+	rdp->core_needs_qs = false;
 	trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
@@ -3972,6 +4242,7 @@ int rcu_cpu_notify(struct notifier_block *self,
 		break;
 	case CPU_ONLINE:
 	case CPU_DOWN_FAILED:
+		sync_sched_exp_online_cleanup(cpu);
 		rcu_boost_kthread_setaffinity(rnp, -1);
 		break;
 	case CPU_DOWN_PREPARE:
@@ -3983,6 +4254,12 @@ int rcu_cpu_notify(struct notifier_block *self,
 			rcu_cleanup_dying_cpu(rsp);
 		break;
 	case CPU_DYING_IDLE:
+		/* QS for any half-done expedited RCU-sched GP. */
+		preempt_disable();
+		rcu_report_exp_rdp(&rcu_sched_state,
+				   this_cpu_ptr(rcu_sched_state.rda), true);
+		preempt_enable();
+
 		for_each_rcu_flavor(rsp) {
 			rcu_cleanup_dying_idle_cpu(cpu, rsp);
 		}
@@ -4114,7 +4391,6 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 	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. */
@@ -4174,18 +4450,13 @@ static void __init rcu_init_one(struct rcu_state *rsp,
 			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]);
+			lockdep_set_class_and_name(&rnp->exp_funnel_mutex,
+						   &rcu_exp_class[i], exp[i]);
 		}
 	}
 
 	init_waitqueue_head(&rsp->gp_wq);
+	init_waitqueue_head(&rsp->expedited_wq);
 	rnp = rsp->level[rcu_num_lvls - 1];
 	for_each_possible_cpu(i) {
 		while (i > rnp->grphi)
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 674ebbc3e406..9fb4e238d4dc 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -70,8 +70,6 @@
 #  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
@@ -81,8 +79,6 @@
 #  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
@@ -93,8 +89,6 @@
 #  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
@@ -106,8 +100,6 @@
 #  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 */
@@ -171,16 +163,21 @@ struct rcu_node {
 				/*  an rcu_data structure, otherwise, each */
 				/*  bit corresponds to a child rcu_node */
 				/*  structure. */
-	unsigned long expmask;	/* Groups that have ->blkd_tasks */
-				/*  elements that need to drain to allow the */
-				/*  current expedited grace period to */
-				/*  complete (only for PREEMPT_RCU). */
 	unsigned long qsmaskinit;
-				/* Per-GP initial value for qsmask & expmask. */
+				/* Per-GP initial value for qsmask. */
 				/*  Initialized from ->qsmaskinitnext at the */
 				/*  beginning of each grace period. */
 	unsigned long qsmaskinitnext;
 				/* Online CPUs for next grace period. */
+	unsigned long expmask;	/* CPUs or groups that need to check in */
+				/*  to allow the current expedited GP */
+				/*  to complete. */
+	unsigned long expmaskinit;
+				/* Per-GP initial values for expmask. */
+				/*  Initialized from ->expmaskinitnext at the */
+				/*  beginning of each expedited GP. */
+	unsigned long expmaskinitnext;
+				/* Online CPUs for next expedited GP. */
 	unsigned long grpmask;	/* Mask to apply to parent qsmask. */
 				/*  Only one bit will be set in this mask. */
 	int	grplo;		/* lowest-numbered CPU or group here. */
@@ -281,6 +278,18 @@ struct rcu_node {
 	for ((rnp) = (rsp)->level[rcu_num_lvls - 1]; \
 	     (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++)
 
+/*
+ * Union to allow "aggregate OR" operation on the need for a quiescent
+ * state by the normal and expedited grace periods.
+ */
+union rcu_noqs {
+	struct {
+		u8 norm;
+		u8 exp;
+	} b; /* Bits. */
+	u16 s; /* Set of bits, aggregate OR here. */
+};
+
 /* Index values for nxttail array in struct rcu_data. */
 #define RCU_DONE_TAIL		0	/* Also RCU_WAIT head. */
 #define RCU_WAIT_TAIL		1	/* Also RCU_NEXT_READY head. */
@@ -297,8 +306,8 @@ struct rcu_data {
 					/*  is aware of having started. */
 	unsigned long	rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */
 					/*  for rcu_all_qs() invocations. */
-	bool		passed_quiesce;	/* User-mode/idle loop etc. */
-	bool		qs_pending;	/* Core waits for quiesc state. */
+	union rcu_noqs	cpu_no_qs;	/* No QSes yet for this CPU. */
+	bool		core_needs_qs;	/* Core waits for quiesc state. */
 	bool		beenonline;	/* CPU online at least once. */
 	bool		gpwrap;		/* Possible gpnum/completed wrap. */
 	struct rcu_node *mynode;	/* This CPU's leaf of hierarchy */
@@ -307,9 +316,6 @@ struct rcu_data {
 					/*  ticks this CPU has handled */
 					/*  during and after the last grace */
 					/* period it is aware of. */
-	struct cpu_stop_work exp_stop_work;
-					/* Expedited grace-period control */
-					/*  for CPU stopping. */
 
 	/* 2) batch handling */
 	/*
@@ -363,7 +369,7 @@ struct rcu_data {
 
 	/* 5) __rcu_pending() statistics. */
 	unsigned long n_rcu_pending;	/* rcu_pending() calls since boot. */
-	unsigned long n_rp_qs_pending;
+	unsigned long n_rp_core_needs_qs;
 	unsigned long n_rp_report_qs;
 	unsigned long n_rp_cb_ready;
 	unsigned long n_rp_cpu_needs_gp;
@@ -378,7 +384,6 @@ struct rcu_data {
 	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
@@ -458,6 +463,7 @@ struct rcu_state {
 	u8 flavor_mask;				/* bit in flavor mask. */
 	struct rcu_data __percpu *rda;		/* pointer of percu rcu_data. */
 	call_rcu_func_t call;			/* call_rcu() flavor. */
+	int ncpus;				/* # CPUs seen so far. */
 
 	/* The following fields are guarded by the root rcu_node's lock. */
 
@@ -499,6 +505,7 @@ struct rcu_state {
 	atomic_long_t expedited_normal;		/* # fallbacks to normal. */
 	atomic_t expedited_need_qs;		/* # CPUs left to check in. */
 	wait_queue_head_t expedited_wq;		/* Wait for check-ins. */
+	int ncpus_snap;				/* # CPUs seen last time. */
 
 	unsigned long jiffies_force_qs;		/* Time at which to invoke */
 						/*  force_quiescent_state(). */
@@ -573,6 +580,7 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 static void rcu_print_detail_task_stall(struct rcu_state *rsp);
 static int rcu_print_task_stall(struct rcu_node *rnp);
+static int rcu_print_task_exp_stall(struct rcu_node *rnp);
 static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
 static void rcu_preempt_check_callbacks(void);
 void call_rcu(struct rcu_head *head, rcu_callback_t func);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 57ed9c13ae5a..630c19772630 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -101,7 +101,6 @@ RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu);
 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,
 			       bool wake);
 
@@ -114,6 +113,147 @@ static void __init rcu_bootup_announce(void)
 	rcu_bootup_announce_oddness();
 }
 
+/* Flags for rcu_preempt_ctxt_queue() decision table. */
+#define RCU_GP_TASKS	0x8
+#define RCU_EXP_TASKS	0x4
+#define RCU_GP_BLKD	0x2
+#define RCU_EXP_BLKD	0x1
+
+/*
+ * Queues a task preempted within an RCU-preempt read-side critical
+ * section into the appropriate location within the ->blkd_tasks list,
+ * depending on the states of any ongoing normal and expedited grace
+ * periods.  The ->gp_tasks pointer indicates which element the normal
+ * grace period is waiting on (NULL if none), and the ->exp_tasks pointer
+ * indicates which element the expedited grace period is waiting on (again,
+ * NULL if none).  If a grace period is waiting on a given element in the
+ * ->blkd_tasks list, it also waits on all subsequent elements.  Thus,
+ * adding a task to the tail of the list blocks any grace period that is
+ * already waiting on one of the elements.  In contrast, adding a task
+ * to the head of the list won't block any grace period that is already
+ * waiting on one of the elements.
+ *
+ * This queuing is imprecise, and can sometimes make an ongoing grace
+ * period wait for a task that is not strictly speaking blocking it.
+ * Given the choice, we needlessly block a normal grace period rather than
+ * blocking an expedited grace period.
+ *
+ * Note that an endless sequence of expedited grace periods still cannot
+ * indefinitely postpone a normal grace period.  Eventually, all of the
+ * fixed number of preempted tasks blocking the normal grace period that are
+ * not also blocking the expedited grace period will resume and complete
+ * their RCU read-side critical sections.  At that point, the ->gp_tasks
+ * pointer will equal the ->exp_tasks pointer, at which point the end of
+ * the corresponding expedited grace period will also be the end of the
+ * normal grace period.
+ */
+static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp,
+				   unsigned long flags) __releases(rnp->lock)
+{
+	int blkd_state = (rnp->gp_tasks ? RCU_GP_TASKS : 0) +
+			 (rnp->exp_tasks ? RCU_EXP_TASKS : 0) +
+			 (rnp->qsmask & rdp->grpmask ? RCU_GP_BLKD : 0) +
+			 (rnp->expmask & rdp->grpmask ? RCU_EXP_BLKD : 0);
+	struct task_struct *t = current;
+
+	/*
+	 * Decide where to queue the newly blocked task.  In theory,
+	 * this could be an if-statement.  In practice, when I tried
+	 * that, it was quite messy.
+	 */
+	switch (blkd_state) {
+	case 0:
+	case                RCU_EXP_TASKS:
+	case                RCU_EXP_TASKS + RCU_GP_BLKD:
+	case RCU_GP_TASKS:
+	case RCU_GP_TASKS + RCU_EXP_TASKS:
+
+		/*
+		 * Blocking neither GP, or first task blocking the normal
+		 * GP but not blocking the already-waiting expedited GP.
+		 * Queue at the head of the list to avoid unnecessarily
+		 * blocking the already-waiting GPs.
+		 */
+		list_add(&t->rcu_node_entry, &rnp->blkd_tasks);
+		break;
+
+	case                                              RCU_EXP_BLKD:
+	case                                RCU_GP_BLKD:
+	case                                RCU_GP_BLKD + RCU_EXP_BLKD:
+	case RCU_GP_TASKS +                               RCU_EXP_BLKD:
+	case RCU_GP_TASKS +                 RCU_GP_BLKD + RCU_EXP_BLKD:
+	case RCU_GP_TASKS + RCU_EXP_TASKS + RCU_GP_BLKD + RCU_EXP_BLKD:
+
+		/*
+		 * First task arriving that blocks either GP, or first task
+		 * arriving that blocks the expedited GP (with the normal
+		 * GP already waiting), or a task arriving that blocks
+		 * both GPs with both GPs already waiting.  Queue at the
+		 * tail of the list to avoid any GP waiting on any of the
+		 * already queued tasks that are not blocking it.
+		 */
+		list_add_tail(&t->rcu_node_entry, &rnp->blkd_tasks);
+		break;
+
+	case                RCU_EXP_TASKS +               RCU_EXP_BLKD:
+	case                RCU_EXP_TASKS + RCU_GP_BLKD + RCU_EXP_BLKD:
+	case RCU_GP_TASKS + RCU_EXP_TASKS +               RCU_EXP_BLKD:
+
+		/*
+		 * Second or subsequent task blocking the expedited GP.
+		 * The task either does not block the normal GP, or is the
+		 * first task blocking the normal GP.  Queue just after
+		 * the first task blocking the expedited GP.
+		 */
+		list_add(&t->rcu_node_entry, rnp->exp_tasks);
+		break;
+
+	case RCU_GP_TASKS +                 RCU_GP_BLKD:
+	case RCU_GP_TASKS + RCU_EXP_TASKS + RCU_GP_BLKD:
+
+		/*
+		 * Second or subsequent task blocking the normal GP.
+		 * The task does not block the expedited GP. Queue just
+		 * after the first task blocking the normal GP.
+		 */
+		list_add(&t->rcu_node_entry, rnp->gp_tasks);
+		break;
+
+	default:
+
+		/* Yet another exercise in excessive paranoia. */
+		WARN_ON_ONCE(1);
+		break;
+	}
+
+	/*
+	 * We have now queued the task.  If it was the first one to
+	 * block either grace period, update the ->gp_tasks and/or
+	 * ->exp_tasks pointers, respectively, to reference the newly
+	 * blocked tasks.
+	 */
+	if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD))
+		rnp->gp_tasks = &t->rcu_node_entry;
+	if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD))
+		rnp->exp_tasks = &t->rcu_node_entry;
+	raw_spin_unlock(&rnp->lock);
+
+	/*
+	 * Report the quiescent state for the expedited GP.  This expedited
+	 * GP should not be able to end until we report, so there should be
+	 * no need to check for a subsequent expedited GP.  (Though we are
+	 * still in a quiescent state in any case.)
+	 */
+	if (blkd_state & RCU_EXP_BLKD &&
+	    t->rcu_read_unlock_special.b.exp_need_qs) {
+		t->rcu_read_unlock_special.b.exp_need_qs = false;
+		rcu_report_exp_rdp(rdp->rsp, rdp, true);
+	} else {
+		WARN_ON_ONCE(t->rcu_read_unlock_special.b.exp_need_qs);
+	}
+	local_irq_restore(flags);
+}
+
 /*
  * Record a preemptible-RCU quiescent state for the specified CPU.  Note
  * that this just means that the task currently running on the CPU is
@@ -125,11 +265,11 @@ static void __init rcu_bootup_announce(void)
  */
 static void rcu_preempt_qs(void)
 {
-	if (!__this_cpu_read(rcu_data_p->passed_quiesce)) {
+	if (__this_cpu_read(rcu_data_p->cpu_no_qs.s)) {
 		trace_rcu_grace_period(TPS("rcu_preempt"),
 				       __this_cpu_read(rcu_data_p->gpnum),
 				       TPS("cpuqs"));
-		__this_cpu_write(rcu_data_p->passed_quiesce, 1);
+		__this_cpu_write(rcu_data_p->cpu_no_qs.b.norm, false);
 		barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */
 		current->rcu_read_unlock_special.b.need_qs = false;
 	}
@@ -167,42 +307,18 @@ static void rcu_preempt_note_context_switch(void)
 		t->rcu_blocked_node = rnp;
 
 		/*
-		 * If this CPU has already checked in, then this task
-		 * will hold up the next grace period rather than the
-		 * current grace period.  Queue the task accordingly.
-		 * If the task is queued for the current grace period
-		 * (i.e., this CPU has not yet passed through a quiescent
-		 * state for the current grace period), then as long
-		 * as that task remains queued, the current grace period
-		 * cannot end.  Note that there is some uncertainty as
-		 * to exactly when the current grace period started.
-		 * We take a conservative approach, which can result
-		 * in unnecessarily waiting on tasks that started very
-		 * slightly after the current grace period began.  C'est
-		 * la vie!!!
-		 *
-		 * But first, note that the current CPU must still be
-		 * on line!
+		 * Verify the CPU's sanity, trace the preemption, and
+		 * then queue the task as required based on the states
+		 * of any ongoing and expedited grace periods.
 		 */
 		WARN_ON_ONCE((rdp->grpmask & rcu_rnp_online_cpus(rnp)) == 0);
 		WARN_ON_ONCE(!list_empty(&t->rcu_node_entry));
-		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;
-			if (IS_ENABLED(CONFIG_RCU_BOOST) &&
-			    rnp->boost_tasks != NULL)
-				rnp->boost_tasks = rnp->gp_tasks;
-		} else {
-			list_add(&t->rcu_node_entry, &rnp->blkd_tasks);
-			if (rnp->qsmask & rdp->grpmask)
-				rnp->gp_tasks = &t->rcu_node_entry;
-		}
 		trace_rcu_preempt_task(rdp->rsp->name,
 				       t->pid,
 				       (rnp->qsmask & rdp->grpmask)
 				       ? rnp->gpnum
 				       : rnp->gpnum + 1);
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		rcu_preempt_ctxt_queue(rnp, rdp, flags);
 	} else if (t->rcu_read_lock_nesting < 0 &&
 		   t->rcu_read_unlock_special.s) {
 
@@ -272,6 +388,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 	unsigned long flags;
 	struct list_head *np;
 	bool drop_boost_mutex = false;
+	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 	union rcu_special special;
 
@@ -282,8 +399,8 @@ void rcu_read_unlock_special(struct task_struct *t)
 	local_irq_save(flags);
 
 	/*
-	 * If RCU core is waiting for this CPU to exit critical section,
-	 * let it know that we have done so.  Because irqs are disabled,
+	 * If RCU core is waiting for this CPU to exit its critical section,
+	 * report the fact that it has exited.  Because irqs are disabled,
 	 * t->rcu_read_unlock_special cannot change.
 	 */
 	special = t->rcu_read_unlock_special;
@@ -296,13 +413,32 @@ void rcu_read_unlock_special(struct task_struct *t)
 		}
 	}
 
+	/*
+	 * Respond to a request for an expedited grace period, but only if
+	 * we were not preempted, meaning that we were running on the same
+	 * CPU throughout.  If we were preempted, the exp_need_qs flag
+	 * would have been cleared at the time of the first preemption,
+	 * and the quiescent state would be reported when we were dequeued.
+	 */
+	if (special.b.exp_need_qs) {
+		WARN_ON_ONCE(special.b.blocked);
+		t->rcu_read_unlock_special.b.exp_need_qs = false;
+		rdp = this_cpu_ptr(rcu_state_p->rda);
+		rcu_report_exp_rdp(rcu_state_p, rdp, true);
+		if (!t->rcu_read_unlock_special.s) {
+			local_irq_restore(flags);
+			return;
+		}
+	}
+
 	/* Hardware IRQ handlers cannot block, complain if they get here. */
 	if (in_irq() || in_serving_softirq()) {
 		lockdep_rcu_suspicious(__FILE__, __LINE__,
 				       "rcu_read_unlock() from irq or softirq with blocking in critical section!!!\n");
-		pr_alert("->rcu_read_unlock_special: %#x (b: %d, nq: %d)\n",
+		pr_alert("->rcu_read_unlock_special: %#x (b: %d, enq: %d nq: %d)\n",
 			 t->rcu_read_unlock_special.s,
 			 t->rcu_read_unlock_special.b.blocked,
+			 t->rcu_read_unlock_special.b.exp_need_qs,
 			 t->rcu_read_unlock_special.b.need_qs);
 		local_irq_restore(flags);
 		return;
@@ -329,7 +465,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 		}
 		empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
-		empty_exp = !rcu_preempted_readers_exp(rnp);
+		empty_exp = sync_rcu_preempt_exp_done(rnp);
 		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
 		np = rcu_next_node_entry(t, rnp);
 		list_del_init(&t->rcu_node_entry);
@@ -353,7 +489,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 		 * Note that rcu_report_unblock_qs_rnp() releases rnp->lock,
 		 * so we must take a snapshot of the expedited state.
 		 */
-		empty_exp_now = !rcu_preempted_readers_exp(rnp);
+		empty_exp_now = sync_rcu_preempt_exp_done(rnp);
 		if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) {
 			trace_rcu_quiescent_state_report(TPS("preempt_rcu"),
 							 rnp->gpnum,
@@ -450,6 +586,27 @@ static int rcu_print_task_stall(struct rcu_node *rnp)
 }
 
 /*
+ * Scan the current list of tasks blocked within RCU read-side critical
+ * sections, printing out the tid of each that is blocking the current
+ * expedited grace period.
+ */
+static int rcu_print_task_exp_stall(struct rcu_node *rnp)
+{
+	struct task_struct *t;
+	int ndetected = 0;
+
+	if (!rnp->exp_tasks)
+		return 0;
+	t = list_entry(rnp->exp_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);
+		ndetected++;
+	}
+	return ndetected;
+}
+
+/*
  * Check that the list of blocked tasks for the newly completed grace
  * period is in fact empty.  It is a serious bug to complete a grace
  * period that still has RCU readers blocked!  This function must be
@@ -483,8 +640,8 @@ static void rcu_preempt_check_callbacks(void)
 		return;
 	}
 	if (t->rcu_read_lock_nesting > 0 &&
-	    __this_cpu_read(rcu_data_p->qs_pending) &&
-	    !__this_cpu_read(rcu_data_p->passed_quiesce))
+	    __this_cpu_read(rcu_data_p->core_needs_qs) &&
+	    __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm))
 		t->rcu_read_unlock_special.b.need_qs = true;
 }
 
@@ -535,155 +692,41 @@ void synchronize_rcu(void)
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu);
 
-static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq);
-
-/*
- * Return non-zero if there are any tasks in RCU read-side critical
- * sections blocking the current preemptible-RCU expedited grace period.
- * If there is no preemptible-RCU expedited grace period currently in
- * progress, returns zero unconditionally.
- */
-static int rcu_preempted_readers_exp(struct rcu_node *rnp)
-{
-	return rnp->exp_tasks != NULL;
-}
-
-/*
- * return non-zero if there is no RCU expedited grace period in progress
- * for the specified rcu_node structure, in other words, if all CPUs and
- * tasks covered by the specified rcu_node structure have done their bit
- * for the current expedited grace period.  Works only for preemptible
- * RCU -- other RCU implementation use other means.
- *
- * Caller must hold the root rcu_node's exp_funnel_mutex.
- */
-static int sync_rcu_preempt_exp_done(struct rcu_node *rnp)
-{
-	return !rcu_preempted_readers_exp(rnp) &&
-	       READ_ONCE(rnp->expmask) == 0;
-}
-
-/*
- * Report the exit from RCU read-side critical section for the last task
- * that queued itself during or before the current expedited preemptible-RCU
- * grace period.  This event is reported either to the rcu_node structure on
- * which the task was queued or to one of that rcu_node structure's ancestors,
- * recursively up the tree.  (Calm down, calm down, we do the recursion
- * iteratively!)
- *
- * 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)
-{
-	unsigned long flags;
-	unsigned long mask;
-
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
-	for (;;) {
-		if (!sync_rcu_preempt_exp_done(rnp)) {
-			raw_spin_unlock_irqrestore(&rnp->lock, flags);
-			break;
-		}
-		if (rnp->parent == NULL) {
-			raw_spin_unlock_irqrestore(&rnp->lock, flags);
-			if (wake) {
-				smp_mb(); /* EGP done before wake_up(). */
-				wake_up(&sync_rcu_preempt_exp_wq);
-			}
-			break;
-		}
-		mask = rnp->grpmask;
-		raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
-		rnp = rnp->parent;
-		raw_spin_lock(&rnp->lock); /* irqs already disabled */
-		smp_mb__after_unlock_lock();
-		rnp->expmask &= ~mask;
-	}
-}
-
 /*
- * Snapshot the tasks blocking the newly started preemptible-RCU expedited
- * grace period for the specified rcu_node structure, phase 1.  If there
- * are such tasks, set the ->expmask bits up the rcu_node tree and also
- * set the ->expmask bits on the leaf rcu_node structures to tell phase 2
- * that work is needed here.
- *
- * Caller must hold the root rcu_node's exp_funnel_mutex.
+ * Remote handler for smp_call_function_single().  If there is an
+ * RCU read-side critical section in effect, request that the
+ * next rcu_read_unlock() record the quiescent state up the
+ * ->expmask fields in the rcu_node tree.  Otherwise, immediately
+ * report the quiescent state.
  */
-static void
-sync_rcu_preempt_exp_init1(struct rcu_state *rsp, struct rcu_node *rnp)
+static void sync_rcu_exp_handler(void *info)
 {
-	unsigned long flags;
-	unsigned long mask;
-	struct rcu_node *rnp_up;
-
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
-	WARN_ON_ONCE(rnp->expmask);
-	WARN_ON_ONCE(rnp->exp_tasks);
-	if (!rcu_preempt_has_tasks(rnp)) {
-		/* No blocked tasks, nothing to do. */
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-		return;
-	}
-	/* Call for Phase 2 and propagate ->expmask bits up the tree. */
-	rnp->expmask = 1;
-	rnp_up = rnp;
-	while (rnp_up->parent) {
-		mask = rnp_up->grpmask;
-		rnp_up = rnp_up->parent;
-		if (rnp_up->expmask & mask)
-			break;
-		raw_spin_lock(&rnp_up->lock); /* irqs already off */
-		smp_mb__after_unlock_lock();
-		rnp_up->expmask |= mask;
-		raw_spin_unlock(&rnp_up->lock); /* irqs still off */
-	}
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
-}
-
-/*
- * Snapshot the tasks blocking the newly started preemptible-RCU expedited
- * grace period for the specified rcu_node structure, phase 2.  If the
- * leaf rcu_node structure has its ->expmask field set, check for tasks.
- * If there are some, clear ->expmask and set ->exp_tasks accordingly,
- * then initiate RCU priority boosting.  Otherwise, clear ->expmask and
- * 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 the root rcu_node's exp_funnel_mutex.
- */
-static void
-sync_rcu_preempt_exp_init2(struct rcu_state *rsp, struct rcu_node *rnp)
-{
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
-	if (!rnp->expmask) {
-		/* Phase 1 didn't do anything, so Phase 2 doesn't either. */
-		raw_spin_unlock_irqrestore(&rnp->lock, flags);
-		return;
-	}
-
-	/* Phase 1 is over. */
-	rnp->expmask = 0;
+	struct rcu_data *rdp;
+	struct rcu_state *rsp = info;
+	struct task_struct *t = current;
 
 	/*
-	 * If there are still blocked tasks, set up ->exp_tasks so that
-	 * rcu_read_unlock_special() will wake us and then boost them.
+	 * Within an RCU read-side critical section, request that the next
+	 * rcu_read_unlock() report.  Unless this RCU read-side critical
+	 * section has already blocked, in which case it is already set
+	 * up for the expedited grace period to wait on it.
 	 */
-	if (rcu_preempt_has_tasks(rnp)) {
-		rnp->exp_tasks = rnp->blkd_tasks.next;
-		rcu_initiate_boost(rnp, flags);  /* releases rnp->lock */
+	if (t->rcu_read_lock_nesting > 0 &&
+	    !t->rcu_read_unlock_special.b.blocked) {
+		t->rcu_read_unlock_special.b.exp_need_qs = true;
 		return;
 	}
 
-	/* No longer any blocked tasks, so undo bit setting. */
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
-	rcu_report_exp_rnp(rsp, rnp, false);
+	/*
+	 * We are either exiting an RCU read-side critical section (negative
+	 * values of t->rcu_read_lock_nesting) or are not in one at all
+	 * (zero value of t->rcu_read_lock_nesting).  Or we are in an RCU
+	 * read-side critical section that blocked before this expedited
+	 * grace period started.  Either way, we can immediately report
+	 * the quiescent state.
+	 */
+	rdp = this_cpu_ptr(rsp->rda);
+	rcu_report_exp_rdp(rsp, rdp, true);
 }
 
 /**
@@ -713,24 +756,12 @@ void synchronize_rcu_expedited(void)
 
 	rcu_exp_gp_seq_start(rsp);
 
-	/* force all RCU readers onto ->blkd_tasks lists. */
-	synchronize_sched_expedited();
-
-	/*
-	 * Snapshot current state of ->blkd_tasks lists into ->expmask.
-	 * Phase 1 sets bits and phase 2 permits rcu_read_unlock_special()
-	 * to start clearing them.  Doing this in one phase leads to
-	 * strange races between setting and clearing bits, so just say "no"!
-	 */
-	rcu_for_each_leaf_node(rsp, rnp)
-		sync_rcu_preempt_exp_init1(rsp, rnp);
-	rcu_for_each_leaf_node(rsp, rnp)
-		sync_rcu_preempt_exp_init2(rsp, rnp);
+	/* Initialize the rcu_node tree in preparation for the wait. */
+	sync_rcu_exp_select_cpus(rsp, sync_rcu_exp_handler);
 
 	/* 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));
+	synchronize_sched_expedited_wait(rsp);
 
 	/* Clean up and exit. */
 	rcu_exp_gp_seq_end(rsp);
@@ -835,6 +866,16 @@ static int rcu_print_task_stall(struct rcu_node *rnp)
 }
 
 /*
+ * Because preemptible RCU does not exist, we never have to check for
+ * tasks blocked within RCU read-side critical sections that are
+ * blocking the current expedited grace period.
+ */
+static int rcu_print_task_exp_stall(struct rcu_node *rnp)
+{
+	return 0;
+}
+
+/*
  * Because there is no preemptible RCU, there can be no readers blocked,
  * so there is no need to check for blocked tasks.  So check only for
  * bogus qsmask values.
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index 1d61f5ba4641..ef7093cc9b5c 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -117,13 +117,13 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 
 	if (!rdp->beenonline)
 		return;
-	seq_printf(m, "%3d%cc=%ld g=%ld pq=%d/%d qp=%d",
+	seq_printf(m, "%3d%cc=%ld g=%ld cnq=%d/%d:%d",
 		   rdp->cpu,
 		   cpu_is_offline(rdp->cpu) ? '!' : ' ',
 		   ulong2long(rdp->completed), ulong2long(rdp->gpnum),
-		   rdp->passed_quiesce,
+		   rdp->cpu_no_qs.b.norm,
 		   rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu),
-		   rdp->qs_pending);
+		   rdp->core_needs_qs);
 	seq_printf(m, " dt=%d/%llx/%d df=%lu",
 		   atomic_read(&rdp->dynticks->dynticks),
 		   rdp->dynticks->dynticks_nesting,
@@ -361,7 +361,7 @@ static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp)
 		   cpu_is_offline(rdp->cpu) ? '!' : ' ',
 		   rdp->n_rcu_pending);
 	seq_printf(m, "qsp=%ld rpq=%ld cbr=%ld cng=%ld ",
-		   rdp->n_rp_qs_pending,
+		   rdp->n_rp_core_needs_qs,
 		   rdp->n_rp_report_qs,
 		   rdp->n_rp_cb_ready,
 		   rdp->n_rp_cpu_needs_gp);