1 files changed, 226 insertions, 200 deletions

diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 0b2c2ad69629..8d18c1014e2b 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -25,39 +25,39 @@
 /*
  * Record the start of an expedited grace period.
  */
-static void rcu_exp_gp_seq_start(struct rcu_state *rsp)
+static void rcu_exp_gp_seq_start(void)
 {
-	rcu_seq_start(&rsp->expedited_sequence);
+	rcu_seq_start(&rcu_state.expedited_sequence);
 }
 
 /*
  * Return then value that expedited-grace-period counter will have
  * at the end of the current grace period.
  */
-static __maybe_unused unsigned long rcu_exp_gp_seq_endval(struct rcu_state *rsp)
+static __maybe_unused unsigned long rcu_exp_gp_seq_endval(void)
 {
-	return rcu_seq_endval(&rsp->expedited_sequence);
+	return rcu_seq_endval(&rcu_state.expedited_sequence);
 }
 
 /*
  * Record the end of an expedited grace period.
  */
-static void rcu_exp_gp_seq_end(struct rcu_state *rsp)
+static void rcu_exp_gp_seq_end(void)
 {
-	rcu_seq_end(&rsp->expedited_sequence);
+	rcu_seq_end(&rcu_state.expedited_sequence);
 	smp_mb(); /* Ensure that consecutive grace periods serialize. */
 }
 
 /*
  * Take a snapshot of the expedited-grace-period counter.
  */
-static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp)
+static unsigned long rcu_exp_gp_seq_snap(void)
 {
 	unsigned long s;
 
 	smp_mb(); /* Caller's modifications seen first by other CPUs. */
-	s = rcu_seq_snap(&rsp->expedited_sequence);
-	trace_rcu_exp_grace_period(rsp->name, s, TPS("snap"));
+	s = rcu_seq_snap(&rcu_state.expedited_sequence);
+	trace_rcu_exp_grace_period(rcu_state.name, s, TPS("snap"));
 	return s;
 }
 
@@ -66,9 +66,9 @@ static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp)
  * if a full expedited grace period has elapsed since that snapshot
  * was taken.
  */
-static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s)
+static bool rcu_exp_gp_seq_done(unsigned long s)
 {
-	return rcu_seq_done(&rsp->expedited_sequence, s);
+	return rcu_seq_done(&rcu_state.expedited_sequence, s);
 }
 
 /*
@@ -78,26 +78,26 @@ static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s)
  * 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)
+static void sync_exp_reset_tree_hotplug(void)
 {
 	bool done;
 	unsigned long flags;
 	unsigned long mask;
 	unsigned long oldmask;
-	int ncpus = smp_load_acquire(&rsp->ncpus); /* Order against locking. */
+	int ncpus = smp_load_acquire(&rcu_state.ncpus); /* Order vs. locking. */
 	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))
+	if (likely(ncpus == rcu_state.ncpus_snap))
 		return;
-	rsp->ncpus_snap = ncpus;
+	rcu_state.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) {
+	rcu_for_each_leaf_node(rnp) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->expmaskinit == rnp->expmaskinitnext) {
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -135,13 +135,13 @@ static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp)
  * 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)
+static void __maybe_unused sync_exp_reset_tree(void)
 {
 	unsigned long flags;
 	struct rcu_node *rnp;
 
-	sync_exp_reset_tree_hotplug(rsp);
-	rcu_for_each_node_breadth_first(rsp, rnp) {
+	sync_exp_reset_tree_hotplug();
+	rcu_for_each_node_breadth_first(rnp) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		WARN_ON_ONCE(rnp->expmask);
 		rnp->expmask = rnp->expmaskinit;
@@ -194,7 +194,7 @@ static bool sync_rcu_preempt_exp_done_unlocked(struct rcu_node *rnp)
  *
  * Caller must hold the specified rcu_node structure's ->lock.
  */
-static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
+static void __rcu_report_exp_rnp(struct rcu_node *rnp,
 				 bool wake, unsigned long flags)
 	__releases(rnp->lock)
 {
@@ -212,7 +212,7 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			if (wake) {
 				smp_mb(); /* EGP done before wake_up(). */
-				swake_up_one(&rsp->expedited_wq);
+				swake_up_one(&rcu_state.expedited_wq);
 			}
 			break;
 		}
@@ -229,20 +229,19 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
  * Report expedited quiescent state for specified node.  This is a
  * lock-acquisition wrapper function for __rcu_report_exp_rnp().
  */
-static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp,
-					      struct rcu_node *rnp, bool wake)
+static void __maybe_unused rcu_report_exp_rnp(struct rcu_node *rnp, bool wake)
 {
 	unsigned long flags;
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	__rcu_report_exp_rnp(rsp, rnp, wake, flags);
+	__rcu_report_exp_rnp(rnp, wake, flags);
 }
 
 /*
  * Report expedited quiescent state for multiple CPUs, all covered by the
  * specified leaf rcu_node structure.
  */
-static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp,
+static void rcu_report_exp_cpu_mult(struct rcu_node *rnp,
 				    unsigned long mask, bool wake)
 {
 	unsigned long flags;
@@ -253,23 +252,23 @@ static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp,
 		return;
 	}
 	rnp->expmask &= ~mask;
-	__rcu_report_exp_rnp(rsp, rnp, wake, flags); /* Releases rnp->lock. */
+	__rcu_report_exp_rnp(rnp, wake, flags); /* Releases rnp->lock. */
 }
 
 /*
  * Report expedited quiescent state for specified rcu_data (CPU).
  */
-static void rcu_report_exp_rdp(struct rcu_state *rsp, struct rcu_data *rdp,
-			       bool wake)
+static void rcu_report_exp_rdp(struct rcu_data *rdp)
 {
-	rcu_report_exp_cpu_mult(rsp, rdp->mynode, rdp->grpmask, wake);
+	WRITE_ONCE(rdp->deferred_qs, false);
+	rcu_report_exp_cpu_mult(rdp->mynode, rdp->grpmask, true);
 }
 
-/* Common code for synchronize_{rcu,sched}_expedited() work-done checking. */
-static bool sync_exp_work_done(struct rcu_state *rsp, unsigned long s)
+/* Common code for work-done checking. */
+static bool sync_exp_work_done(unsigned long s)
 {
-	if (rcu_exp_gp_seq_done(rsp, s)) {
-		trace_rcu_exp_grace_period(rsp->name, s, TPS("done"));
+	if (rcu_exp_gp_seq_done(s)) {
+		trace_rcu_exp_grace_period(rcu_state.name, s, TPS("done"));
 		/* Ensure test happens before caller kfree(). */
 		smp_mb__before_atomic(); /* ^^^ */
 		return true;
@@ -284,28 +283,28 @@ static bool sync_exp_work_done(struct rcu_state *rsp, unsigned long s)
  * with the mutex held, indicating that the caller must actually do the
  * expedited grace period.
  */
-static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
+static bool exp_funnel_lock(unsigned long s)
 {
-	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
+	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, raw_smp_processor_id());
 	struct rcu_node *rnp = rdp->mynode;
-	struct rcu_node *rnp_root = rcu_get_root(rsp);
+	struct rcu_node *rnp_root = rcu_get_root();
 
 	/* Low-contention fastpath. */
 	if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s) &&
 	    (rnp == rnp_root ||
 	     ULONG_CMP_LT(READ_ONCE(rnp_root->exp_seq_rq), s)) &&
-	    mutex_trylock(&rsp->exp_mutex))
+	    mutex_trylock(&rcu_state.exp_mutex))
 		goto fastpath;
 
 	/*
 	 * 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 to acquire rsp->exp_mutex.  The mapping
+	 * otherwise falls through to acquire ->exp_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.
 	 */
 	for (; rnp != NULL; rnp = rnp->parent) {
-		if (sync_exp_work_done(rsp, s))
+		if (sync_exp_work_done(s))
 			return true;
 
 		/* Work not done, either wait here or go up. */
@@ -314,68 +313,29 @@ static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
 
 			/* Someone else doing GP, so wait for them. */
 			spin_unlock(&rnp->exp_lock);
-			trace_rcu_exp_funnel_lock(rsp->name, rnp->level,
+			trace_rcu_exp_funnel_lock(rcu_state.name, rnp->level,
 						  rnp->grplo, rnp->grphi,
 						  TPS("wait"));
 			wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
-				   sync_exp_work_done(rsp, s));
+				   sync_exp_work_done(s));
 			return true;
 		}
 		rnp->exp_seq_rq = s; /* Followers can wait on us. */
 		spin_unlock(&rnp->exp_lock);
-		trace_rcu_exp_funnel_lock(rsp->name, rnp->level, rnp->grplo,
-					  rnp->grphi, TPS("nxtlvl"));
+		trace_rcu_exp_funnel_lock(rcu_state.name, rnp->level,
+					  rnp->grplo, rnp->grphi, TPS("nxtlvl"));
 	}
-	mutex_lock(&rsp->exp_mutex);
+	mutex_lock(&rcu_state.exp_mutex);
 fastpath:
-	if (sync_exp_work_done(rsp, s)) {
-		mutex_unlock(&rsp->exp_mutex);
+	if (sync_exp_work_done(s)) {
+		mutex_unlock(&rcu_state.exp_mutex);
 		return true;
 	}
-	rcu_exp_gp_seq_start(rsp);
-	trace_rcu_exp_grace_period(rsp->name, s, TPS("start"));
+	rcu_exp_gp_seq_start();
+	trace_rcu_exp_grace_period(rcu_state.name, s, TPS("start"));
 	return false;
 }
 
-/* Invoked on each online non-idle CPU for expedited quiescent state. */
-static void sync_sched_exp_handler(void *data)
-{
-	struct rcu_data *rdp;
-	struct rcu_node *rnp;
-	struct rcu_state *rsp = data;
-
-	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;
-	if (rcu_is_cpu_rrupt_from_idle()) {
-		rcu_report_exp_rdp(&rcu_sched_state,
-				   this_cpu_ptr(&rcu_sched_data), true);
-		return;
-	}
-	__this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, true);
-	/* Store .exp before .rcu_urgent_qs. */
-	smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), 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 CPUs within the specified rcu_node that the upcoming
  * expedited grace period needs to wait for.
@@ -391,7 +351,6 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
 	struct rcu_exp_work *rewp =
 		container_of(wp, struct rcu_exp_work, rew_work);
 	struct rcu_node *rnp = container_of(rewp, struct rcu_node, rew);
-	struct rcu_state *rsp = rewp->rew_rsp;
 
 	func = rewp->rew_func;
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
@@ -400,15 +359,14 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
 	mask_ofl_test = 0;
 	for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
 		unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
-		struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
-		struct rcu_dynticks *rdtp = per_cpu_ptr(&rcu_dynticks, cpu);
+		struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 		int snap;
 
 		if (raw_smp_processor_id() == cpu ||
 		    !(rnp->qsmaskinitnext & mask)) {
 			mask_ofl_test |= mask;
 		} else {
-			snap = rcu_dynticks_snap(rdtp);
+			snap = rcu_dynticks_snap(rdp);
 			if (rcu_dynticks_in_eqs(snap))
 				mask_ofl_test |= mask;
 			else
@@ -429,17 +387,16 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
 	/* IPI the remaining CPUs for expedited quiescent state. */
 	for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) {
 		unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
-		struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
+		struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 
 		if (!(mask_ofl_ipi & mask))
 			continue;
 retry_ipi:
-		if (rcu_dynticks_in_eqs_since(rdp->dynticks,
-					      rdp->exp_dynticks_snap)) {
+		if (rcu_dynticks_in_eqs_since(rdp, rdp->exp_dynticks_snap)) {
 			mask_ofl_test |= mask;
 			continue;
 		}
-		ret = smp_call_function_single(cpu, func, rsp, 0);
+		ret = smp_call_function_single(cpu, func, NULL, 0);
 		if (!ret) {
 			mask_ofl_ipi &= ~mask;
 			continue;
@@ -450,7 +407,7 @@ retry_ipi:
 		    (rnp->expmask & mask)) {
 			/* Online, so delay for a bit and try again. */
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-			trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("selectofl"));
+			trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("selectofl"));
 			schedule_timeout_uninterruptible(1);
 			goto retry_ipi;
 		}
@@ -462,33 +419,31 @@ retry_ipi:
 	/* 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);
+		rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false);
 }
 
 /*
  * 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)
+static void sync_rcu_exp_select_cpus(smp_call_func_t func)
 {
 	int cpu;
 	struct rcu_node *rnp;
 
-	trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("reset"));
-	sync_exp_reset_tree(rsp);
-	trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("select"));
+	trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("reset"));
+	sync_exp_reset_tree();
+	trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("select"));
 
 	/* Schedule work for each leaf rcu_node structure. */
-	rcu_for_each_leaf_node(rsp, rnp) {
+	rcu_for_each_leaf_node(rnp) {
 		rnp->exp_need_flush = false;
 		if (!READ_ONCE(rnp->expmask))
 			continue; /* Avoid early boot non-existent wq. */
 		rnp->rew.rew_func = func;
-		rnp->rew.rew_rsp = rsp;
 		if (!READ_ONCE(rcu_par_gp_wq) ||
 		    rcu_scheduler_active != RCU_SCHEDULER_RUNNING ||
-		    rcu_is_last_leaf_node(rsp, rnp)) {
+		    rcu_is_last_leaf_node(rnp)) {
 			/* No workqueues yet or last leaf, do direct call. */
 			sync_rcu_exp_select_node_cpus(&rnp->rew.rew_work);
 			continue;
@@ -505,12 +460,12 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 	}
 
 	/* Wait for workqueue jobs (if any) to complete. */
-	rcu_for_each_leaf_node(rsp, rnp)
+	rcu_for_each_leaf_node(rnp)
 		if (rnp->exp_need_flush)
 			flush_work(&rnp->rew.rew_work);
 }
 
-static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
+static void synchronize_sched_expedited_wait(void)
 {
 	int cpu;
 	unsigned long jiffies_stall;
@@ -518,16 +473,16 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 	unsigned long mask;
 	int ndetected;
 	struct rcu_node *rnp;
-	struct rcu_node *rnp_root = rcu_get_root(rsp);
+	struct rcu_node *rnp_root = rcu_get_root();
 	int ret;
 
-	trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("startwait"));
+	trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("startwait"));
 	jiffies_stall = rcu_jiffies_till_stall_check();
 	jiffies_start = jiffies;
 
 	for (;;) {
 		ret = swait_event_timeout_exclusive(
-				rsp->expedited_wq,
+				rcu_state.expedited_wq,
 				sync_rcu_preempt_exp_done_unlocked(rnp_root),
 				jiffies_stall);
 		if (ret > 0 || sync_rcu_preempt_exp_done_unlocked(rnp_root))
@@ -537,9 +492,9 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 			continue;
 		panic_on_rcu_stall();
 		pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {",
-		       rsp->name);
+		       rcu_state.name);
 		ndetected = 0;
-		rcu_for_each_leaf_node(rsp, rnp) {
+		rcu_for_each_leaf_node(rnp) {
 			ndetected += rcu_print_task_exp_stall(rnp);
 			for_each_leaf_node_possible_cpu(rnp, cpu) {
 				struct rcu_data *rdp;
@@ -548,7 +503,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 				if (!(rnp->expmask & mask))
 					continue;
 				ndetected++;
-				rdp = per_cpu_ptr(rsp->rda, cpu);
+				rdp = per_cpu_ptr(&rcu_data, cpu);
 				pr_cont(" %d-%c%c%c", cpu,
 					"O."[!!cpu_online(cpu)],
 					"o."[!!(rdp->grpmask & rnp->expmaskinit)],
@@ -556,11 +511,11 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 			}
 		}
 		pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n",
-			jiffies - jiffies_start, rsp->expedited_sequence,
+			jiffies - jiffies_start, rcu_state.expedited_sequence,
 			rnp_root->expmask, ".T"[!!rnp_root->exp_tasks]);
 		if (ndetected) {
 			pr_err("blocking rcu_node structures:");
-			rcu_for_each_node_breadth_first(rsp, rnp) {
+			rcu_for_each_node_breadth_first(rnp) {
 				if (rnp == rnp_root)
 					continue; /* printed unconditionally */
 				if (sync_rcu_preempt_exp_done_unlocked(rnp))
@@ -572,7 +527,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 			}
 			pr_cont("\n");
 		}
-		rcu_for_each_leaf_node(rsp, rnp) {
+		rcu_for_each_leaf_node(rnp) {
 			for_each_leaf_node_possible_cpu(rnp, cpu) {
 				mask = leaf_node_cpu_bit(rnp, cpu);
 				if (!(rnp->expmask & mask))
@@ -590,21 +545,21 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
  * grace period.  Also update all the ->exp_seq_rq counters as needed
  * in order to avoid counter-wrap problems.
  */
-static void rcu_exp_wait_wake(struct rcu_state *rsp, unsigned long s)
+static void rcu_exp_wait_wake(unsigned long s)
 {
 	struct rcu_node *rnp;
 
-	synchronize_sched_expedited_wait(rsp);
-	rcu_exp_gp_seq_end(rsp);
-	trace_rcu_exp_grace_period(rsp->name, s, TPS("end"));
+	synchronize_sched_expedited_wait();
+	rcu_exp_gp_seq_end();
+	trace_rcu_exp_grace_period(rcu_state.name, s, TPS("end"));
 
 	/*
 	 * Switch over to wakeup mode, allowing the next GP, but -only- the
 	 * next GP, to proceed.
 	 */
-	mutex_lock(&rsp->exp_wake_mutex);
+	mutex_lock(&rcu_state.exp_wake_mutex);
 
-	rcu_for_each_node_breadth_first(rsp, rnp) {
+	rcu_for_each_node_breadth_first(rnp) {
 		if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s)) {
 			spin_lock(&rnp->exp_lock);
 			/* Recheck, avoid hang in case someone just arrived. */
@@ -613,24 +568,23 @@ static void rcu_exp_wait_wake(struct rcu_state *rsp, unsigned long s)
 			spin_unlock(&rnp->exp_lock);
 		}
 		smp_mb(); /* All above changes before wakeup. */
-		wake_up_all(&rnp->exp_wq[rcu_seq_ctr(rsp->expedited_sequence) & 0x3]);
+		wake_up_all(&rnp->exp_wq[rcu_seq_ctr(rcu_state.expedited_sequence) & 0x3]);
 	}
-	trace_rcu_exp_grace_period(rsp->name, s, TPS("endwake"));
-	mutex_unlock(&rsp->exp_wake_mutex);
+	trace_rcu_exp_grace_period(rcu_state.name, s, TPS("endwake"));
+	mutex_unlock(&rcu_state.exp_wake_mutex);
 }
 
 /*
  * Common code to drive an expedited grace period forward, used by
  * workqueues and mid-boot-time tasks.
  */
-static void rcu_exp_sel_wait_wake(struct rcu_state *rsp,
-				  smp_call_func_t func, unsigned long s)
+static void rcu_exp_sel_wait_wake(smp_call_func_t func, unsigned long s)
 {
 	/* Initialize the rcu_node tree in preparation for the wait. */
-	sync_rcu_exp_select_cpus(rsp, func);
+	sync_rcu_exp_select_cpus(func);
 
 	/* Wait and clean up, including waking everyone. */
-	rcu_exp_wait_wake(rsp, s);
+	rcu_exp_wait_wake(s);
 }
 
 /*
@@ -641,15 +595,14 @@ static void wait_rcu_exp_gp(struct work_struct *wp)
 	struct rcu_exp_work *rewp;
 
 	rewp = container_of(wp, struct rcu_exp_work, rew_work);
-	rcu_exp_sel_wait_wake(rewp->rew_rsp, rewp->rew_func, rewp->rew_s);
+	rcu_exp_sel_wait_wake(rewp->rew_func, rewp->rew_s);
 }
 
 /*
- * Given an rcu_state pointer and a smp_call_function() handler, kick
- * off the specified flavor of expedited grace period.
+ * Given a smp_call_function() handler, kick off the specified
+ * implementation of expedited grace period.
  */
-static void _synchronize_rcu_expedited(struct rcu_state *rsp,
-				       smp_call_func_t func)
+static void _synchronize_rcu_expedited(smp_call_func_t func)
 {
 	struct rcu_data *rdp;
 	struct rcu_exp_work rew;
@@ -658,71 +611,37 @@ static void _synchronize_rcu_expedited(struct rcu_state *rsp,
 
 	/* If expedited grace periods are prohibited, fall back to normal. */
 	if (rcu_gp_is_normal()) {
-		wait_rcu_gp(rsp->call);
+		wait_rcu_gp(call_rcu);
 		return;
 	}
 
 	/* Take a snapshot of the sequence number.  */
-	s = rcu_exp_gp_seq_snap(rsp);
-	if (exp_funnel_lock(rsp, s))
+	s = rcu_exp_gp_seq_snap();
+	if (exp_funnel_lock(s))
 		return;  /* Someone else did our work for us. */
 
 	/* Ensure that load happens before action based on it. */
 	if (unlikely(rcu_scheduler_active == RCU_SCHEDULER_INIT)) {
 		/* Direct call during scheduler init and early_initcalls(). */
-		rcu_exp_sel_wait_wake(rsp, func, s);
+		rcu_exp_sel_wait_wake(func, s);
 	} else {
 		/* Marshall arguments & schedule the expedited grace period. */
 		rew.rew_func = func;
-		rew.rew_rsp = rsp;
 		rew.rew_s = s;
 		INIT_WORK_ONSTACK(&rew.rew_work, wait_rcu_exp_gp);
 		queue_work(rcu_gp_wq, &rew.rew_work);
 	}
 
 	/* Wait for expedited grace period to complete. */
-	rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
-	rnp = rcu_get_root(rsp);
+	rdp = per_cpu_ptr(&rcu_data, raw_smp_processor_id());
+	rnp = rcu_get_root();
 	wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3],
-		   sync_exp_work_done(rsp, s));
+		   sync_exp_work_done(s));
 	smp_mb(); /* Workqueue actions happen before return. */
 
 	/* Let the next expedited grace period start. */
-	mutex_unlock(&rsp->exp_mutex);
-}
-
-/**
- * synchronize_sched_expedited - Brute-force RCU-sched grace period
- *
- * Wait for an RCU-sched grace period to elapse, but use a "big hammer"
- * approach to force the grace period to end quickly.  This consumes
- * significant time on all CPUs and is unfriendly to real-time workloads,
- * so is thus not recommended for any sort of common-case code.  In fact,
- * if you are using synchronize_sched_expedited() in a loop, please
- * 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 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)
-{
-	struct rcu_state *rsp = &rcu_sched_state;
-
-	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_expedited() in RCU read-side critical section");
-
-	/* If only one CPU, this is automatically a grace period. */
-	if (rcu_blocking_is_gp())
-		return;
-
-	_synchronize_rcu_expedited(rsp, sync_sched_exp_handler);
+	mutex_unlock(&rcu_state.exp_mutex);
 }
-EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
 
 #ifdef CONFIG_PREEMPT_RCU
 
@@ -733,34 +652,78 @@ EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
  * ->expmask fields in the rcu_node tree.  Otherwise, immediately
  * report the quiescent state.
  */
-static void sync_rcu_exp_handler(void *info)
+static void sync_rcu_exp_handler(void *unused)
 {
-	struct rcu_data *rdp;
-	struct rcu_state *rsp = info;
+	unsigned long flags;
+	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+	struct rcu_node *rnp = rdp->mynode;
 	struct task_struct *t = current;
 
 	/*
-	 * 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.
+	 * First, the common case of not being in an RCU read-side
+	 * critical section.  If also enabled or idle, immediately
+	 * report the quiescent state, otherwise defer.
 	 */
-	if (t->rcu_read_lock_nesting > 0 &&
-	    !t->rcu_read_unlock_special.b.blocked) {
-		t->rcu_read_unlock_special.b.exp_need_qs = true;
+	if (!t->rcu_read_lock_nesting) {
+		if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) ||
+		    rcu_dynticks_curr_cpu_in_eqs()) {
+			rcu_report_exp_rdp(rdp);
+		} else {
+			rdp->deferred_qs = true;
+			set_tsk_need_resched(t);
+			set_preempt_need_resched();
+		}
 		return;
 	}
 
 	/*
-	 * 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.
+	 * Second, the less-common case of being in an RCU read-side
+	 * critical section.  In this case we can count on a future
+	 * rcu_read_unlock().  However, this rcu_read_unlock() might
+	 * execute on some other CPU, but in that case there will be
+	 * a future context switch.  Either way, if the expedited
+	 * grace period is still waiting on this CPU, set ->deferred_qs
+	 * so that the eventual quiescent state will be reported.
+	 * Note that there is a large group of race conditions that
+	 * can have caused this quiescent state to already have been
+	 * reported, so we really do need to check ->expmask.
+	 */
+	if (t->rcu_read_lock_nesting > 0) {
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
+		if (rnp->expmask & rdp->grpmask)
+			rdp->deferred_qs = true;
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	}
+
+	/*
+	 * The final and least likely case is where the interrupted
+	 * code was just about to or just finished exiting the RCU-preempt
+	 * read-side critical section, and no, we can't tell which.
+	 * So either way, set ->deferred_qs to flag later code that
+	 * a quiescent state is required.
+	 *
+	 * If the CPU is fully enabled (or if some buggy RCU-preempt
+	 * read-side critical section is being used from idle), just
+	 * invoke rcu_preempt_defer_qs() to immediately report the
+	 * quiescent state.  We cannot use rcu_read_unlock_special()
+	 * because we are in an interrupt handler, which will cause that
+	 * function to take an early exit without doing anything.
+	 *
+	 * Otherwise, force a context switch after the CPU enables everything.
 	 */
-	rdp = this_cpu_ptr(rsp->rda);
-	rcu_report_exp_rdp(rsp, rdp, true);
+	rdp->deferred_qs = true;
+	if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) ||
+	    WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs())) {
+		rcu_preempt_deferred_qs(t);
+	} else {
+		set_tsk_need_resched(t);
+		set_preempt_need_resched();
+	}
+}
+
+/* PREEMPT=y, so no PREEMPT=n expedited grace period to clean up after. */
+static void sync_sched_exp_online_cleanup(int cpu)
+{
 }
 
 /**
@@ -780,11 +743,11 @@ static void sync_rcu_exp_handler(void *info)
  * you are using synchronize_rcu_expedited() in a loop, please restructure
  * your code to batch your updates, and then Use a single synchronize_rcu()
  * instead.
+ *
+ * This has the same semantics as (but is more brutal than) synchronize_rcu().
  */
 void synchronize_rcu_expedited(void)
 {
-	struct rcu_state *rsp = rcu_state_p;
-
 	RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
 			 lock_is_held(&rcu_lock_map) ||
 			 lock_is_held(&rcu_sched_lock_map),
@@ -792,19 +755,82 @@ void synchronize_rcu_expedited(void)
 
 	if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
 		return;
-	_synchronize_rcu_expedited(rsp, sync_rcu_exp_handler);
+	_synchronize_rcu_expedited(sync_rcu_exp_handler);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
 
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
+/* Invoked on each online non-idle CPU for expedited quiescent state. */
+static void sync_sched_exp_handler(void *unused)
+{
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
+
+	rdp = this_cpu_ptr(&rcu_data);
+	rnp = rdp->mynode;
+	if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) ||
+	    __this_cpu_read(rcu_data.cpu_no_qs.b.exp))
+		return;
+	if (rcu_is_cpu_rrupt_from_idle()) {
+		rcu_report_exp_rdp(this_cpu_ptr(&rcu_data));
+		return;
+	}
+	__this_cpu_write(rcu_data.cpu_no_qs.b.exp, true);
+	/* Store .exp before .rcu_urgent_qs. */
+	smp_store_release(this_cpu_ptr(&rcu_data.rcu_urgent_qs), true);
+	set_tsk_need_resched(current);
+	set_preempt_need_resched();
+}
+
+/* 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;
+
+	rdp = per_cpu_ptr(&rcu_data, cpu);
+	rnp = rdp->mynode;
+	if (!(READ_ONCE(rnp->expmask) & rdp->grpmask))
+		return;
+	ret = smp_call_function_single(cpu, sync_sched_exp_handler, NULL, 0);
+	WARN_ON_ONCE(ret);
+}
+
 /*
- * Wait for an rcu-preempt grace period, but make it happen quickly.
- * But because preemptible RCU does not exist, map to rcu-sched.
+ * Because a context switch is a grace period for !PREEMPT, any
+ * blocking grace-period wait automatically implies a grace period if
+ * there is only one CPU online at any point time during execution of
+ * either synchronize_rcu() or synchronize_rcu_expedited().  It is OK to
+ * occasionally incorrectly indicate that there are multiple CPUs online
+ * when there was in fact only one the whole time, as this just adds some
+ * overhead: RCU still operates correctly.
  */
+static int rcu_blocking_is_gp(void)
+{
+	int ret;
+
+	might_sleep();  /* Check for RCU read-side critical section. */
+	preempt_disable();
+	ret = num_online_cpus() <= 1;
+	preempt_enable();
+	return ret;
+}
+
+/* PREEMPT=n implementation of synchronize_rcu_expedited(). */
 void synchronize_rcu_expedited(void)
 {
-	synchronize_sched_expedited();
+	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_expedited() in RCU read-side critical section");
+
+	/* If only one CPU, this is automatically a grace period. */
+	if (rcu_blocking_is_gp())
+		return;
+
+	_synchronize_rcu_expedited(sync_sched_exp_handler);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);