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 changes in this cycle were:

   - Adding transitivity uniformly to rcu_node structure ->lock
     acquisitions.  (This is implemented by the first two commits on top
     of v4.4-rc2 due to the pervasive nature of this change.)

   - Documentation updates, including RCU requirements.

   - Expedited grace-period changes.

   - Miscellaneous fixes.

   - Linked-list fixes, courtesy of KTSAN.

   - Torture-test updates.

   - Late-breaking fix to sysrq-generated crash.

  One thing I should note is that these pieces of documentation are
  fairly large files:

    .../RCU/Design/Requirements/Requirements.html      | 2897 ++++++++++++++++++++
    .../RCU/Design/Requirements/Requirements.htmlx     | 2741 ++++++++++++++++++

  and are written in HTML, not the usual .txt style.  I hope they are
  fine"

Paul McKenney explains the html docs:
 "For whatever it is worth, the reason for this unconventional choice
  was that attempts to do the diagrams in ASCII art failed miserably.

  And attempts to do ASCII art for the upcoming documentation of the
  data structures failed even more miserably"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (49 commits)
  sysrq: Fix warning in sysrq generated crash.
  list: Add lockless list traversal primitives
  rcu: Make rcu_gp_init() be bool rather than int
  rcu: Move wakeup out from under rnp->lock
  rcu: Fix comment for rcu_dereference_raw_notrace
  rcu: Don't redundantly disable irqs in rcu_irq_{enter,exit}()
  rcu: Make cpu_needs_another_gp() be bool
  rcu: Eliminate unused rcu_init_one() argument
  rcu: Remove TINY_RCU bloat from pointless boot parameters
  torture: Place console.log files correctly from the get-go
  torture: Abbreviate console error dump
  rcutorture: Print symbolic name for ->gp_state
  rcutorture: Print symbolic name for rcu_torture_writer_state
  rcutorture: Remove CONFIG_RCU_USER_QS from rcutorture selftest doc
  rcutorture: Default grace period to three minutes, allow override
  rcutorture:  Dump stack when GP kthread stalls
  rcutorture: Flag nonexistent RCU GP kthread
  rcutorture: Add batch number to script printout
  Documentation/memory-barriers.txt: Fix ACCESS_ONCE thinko
  documentation: Update RCU requirements based on expedited changes
  ...

9 files changed, 342 insertions, 217 deletions

diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index e83b26464061..152da4a48867 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -20,7 +20,7 @@
 #include <linux/capability.h>
 #include <linux/compiler.h>
 
-#include <linux/rcupdate.h>	/* rcu_expedited */
+#include <linux/rcupdate.h>	/* rcu_expedited and rcu_normal */
 
 #define KERNEL_ATTR_RO(_name) \
 static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
@@ -144,11 +144,12 @@ static ssize_t fscaps_show(struct kobject *kobj,
 }
 KERNEL_ATTR_RO(fscaps);
 
+#ifndef CONFIG_TINY_RCU
 int rcu_expedited;
 static ssize_t rcu_expedited_show(struct kobject *kobj,
 				  struct kobj_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%d\n", rcu_expedited);
+	return sprintf(buf, "%d\n", READ_ONCE(rcu_expedited));
 }
 static ssize_t rcu_expedited_store(struct kobject *kobj,
 				   struct kobj_attribute *attr,
@@ -161,6 +162,24 @@ static ssize_t rcu_expedited_store(struct kobject *kobj,
 }
 KERNEL_ATTR_RW(rcu_expedited);
 
+int rcu_normal;
+static ssize_t rcu_normal_show(struct kobject *kobj,
+			       struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", READ_ONCE(rcu_normal));
+}
+static ssize_t rcu_normal_store(struct kobject *kobj,
+				struct kobj_attribute *attr,
+				const char *buf, size_t count)
+{
+	if (kstrtoint(buf, 0, &rcu_normal))
+		return -EINVAL;
+
+	return count;
+}
+KERNEL_ATTR_RW(rcu_normal);
+#endif /* #ifndef CONFIG_TINY_RCU */
+
 /*
  * Make /sys/kernel/notes give the raw contents of our kernel .notes section.
  */
@@ -202,7 +221,10 @@ static struct attribute * kernel_attrs[] = {
 	&kexec_crash_size_attr.attr,
 	&vmcoreinfo_attr.attr,
 #endif
+#ifndef CONFIG_TINY_RCU
 	&rcu_expedited_attr.attr,
+	&rcu_normal_attr.attr,
+#endif
 	NULL
 };
 
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index d89328e260df..d2988d047d66 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -162,6 +162,27 @@ static int rcu_torture_writer_state;
 #define RTWS_SYNC		7
 #define RTWS_STUTTER		8
 #define RTWS_STOPPING		9
+static const char * const rcu_torture_writer_state_names[] = {
+	"RTWS_FIXED_DELAY",
+	"RTWS_DELAY",
+	"RTWS_REPLACE",
+	"RTWS_DEF_FREE",
+	"RTWS_EXP_SYNC",
+	"RTWS_COND_GET",
+	"RTWS_COND_SYNC",
+	"RTWS_SYNC",
+	"RTWS_STUTTER",
+	"RTWS_STOPPING",
+};
+
+static const char *rcu_torture_writer_state_getname(void)
+{
+	unsigned int i = READ_ONCE(rcu_torture_writer_state);
+
+	if (i >= ARRAY_SIZE(rcu_torture_writer_state_names))
+		return "???";
+	return rcu_torture_writer_state_names[i];
+}
 
 #if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE)
 #define RCUTORTURE_RUNNABLE_INIT 1
@@ -1307,7 +1328,8 @@ rcu_torture_stats_print(void)
 
 		rcutorture_get_gp_data(cur_ops->ttype,
 				       &flags, &gpnum, &completed);
-		pr_alert("??? Writer stall state %d g%lu c%lu f%#x\n",
+		pr_alert("??? Writer stall state %s(%d) g%lu c%lu f%#x\n",
+			 rcu_torture_writer_state_getname(),
 			 rcu_torture_writer_state,
 			 gpnum, completed, flags);
 		show_rcu_gp_kthreads();
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index a63a1ea5a41b..9b9cdd549caa 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -489,7 +489,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
  */
 void synchronize_srcu(struct srcu_struct *sp)
 {
-	__synchronize_srcu(sp, rcu_gp_is_expedited()
+	__synchronize_srcu(sp, (rcu_gp_is_expedited() && !rcu_gp_is_normal())
 			   ? SYNCHRONIZE_SRCU_EXP_TRYCOUNT
 			   : SYNCHRONIZE_SRCU_TRYCOUNT);
 }
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index f07343b54fe5..e41dd4131f7a 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -68,10 +68,6 @@ MODULE_ALIAS("rcutree");
 
 /* Data structures. */
 
-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];
-
 /*
  * In order to export the rcu_state name to the tracing tools, it
  * needs to be added in the __tracepoint_string section.
@@ -246,24 +242,17 @@ static int rcu_gp_in_progress(struct rcu_state *rsp)
  */
 void rcu_sched_qs(void)
 {
-	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.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);
-	}
+	if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.s))
+		return;
+	trace_rcu_grace_period(TPS("rcu_sched"),
+			       __this_cpu_read(rcu_sched_data.gpnum),
+			       TPS("cpuqs"));
+	__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;
+	__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);
 }
 
 void rcu_bh_qs(void)
@@ -300,17 +289,16 @@ EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr);
  * We inform the RCU core by emulating a zero-duration dyntick-idle
  * period, which we in turn do by incrementing the ->dynticks counter
  * by two.
+ *
+ * The caller must have disabled interrupts.
  */
 static void rcu_momentary_dyntick_idle(void)
 {
-	unsigned long flags;
 	struct rcu_data *rdp;
 	struct rcu_dynticks *rdtp;
 	int resched_mask;
 	struct rcu_state *rsp;
 
-	local_irq_save(flags);
-
 	/*
 	 * Yes, we can lose flag-setting operations.  This is OK, because
 	 * the flag will be set again after some delay.
@@ -340,13 +328,12 @@ static void rcu_momentary_dyntick_idle(void)
 		smp_mb__after_atomic(); /* Later stuff after QS. */
 		break;
 	}
-	local_irq_restore(flags);
 }
 
 /*
  * Note a context switch.  This is a quiescent state for RCU-sched,
  * and requires special handling for preemptible RCU.
- * The caller must have disabled preemption.
+ * The caller must have disabled interrupts.
  */
 void rcu_note_context_switch(void)
 {
@@ -376,9 +363,14 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch);
  */
 void rcu_all_qs(void)
 {
+	unsigned long flags;
+
 	barrier(); /* Avoid RCU read-side critical sections leaking down. */
-	if (unlikely(raw_cpu_read(rcu_sched_qs_mask)))
+	if (unlikely(raw_cpu_read(rcu_sched_qs_mask))) {
+		local_irq_save(flags);
 		rcu_momentary_dyntick_idle();
+		local_irq_restore(flags);
+	}
 	this_cpu_inc(rcu_qs_ctr);
 	barrier(); /* Avoid RCU read-side critical sections leaking up. */
 }
@@ -605,25 +597,25 @@ static int rcu_future_needs_gp(struct rcu_state *rsp)
  * The caller must have disabled interrupts to prevent races with
  * normal callback registry.
  */
-static int
+static bool
 cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp)
 {
 	int i;
 
 	if (rcu_gp_in_progress(rsp))
-		return 0;  /* No, a grace period is already in progress. */
+		return false;  /* No, a grace period is already in progress. */
 	if (rcu_future_needs_gp(rsp))
-		return 1;  /* Yes, a no-CBs CPU needs one. */
+		return true;  /* Yes, a no-CBs CPU needs one. */
 	if (!rdp->nxttail[RCU_NEXT_TAIL])
-		return 0;  /* No, this is a no-CBs (or offline) CPU. */
+		return false;  /* No, this is a no-CBs (or offline) CPU. */
 	if (*rdp->nxttail[RCU_NEXT_READY_TAIL])
-		return 1;  /* Yes, this CPU has newly registered callbacks. */
+		return true;  /* Yes, CPU has newly registered callbacks. */
 	for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++)
 		if (rdp->nxttail[i - 1] != rdp->nxttail[i] &&
 		    ULONG_CMP_LT(READ_ONCE(rsp->completed),
 				 rdp->nxtcompleted[i]))
-			return 1;  /* Yes, CBs for future grace period. */
-	return 0; /* No grace period needed. */
+			return true;  /* Yes, CBs for future grace period. */
+	return false; /* No grace period needed. */
 }
 
 /*
@@ -740,7 +732,7 @@ void rcu_user_enter(void)
  *
  * Exit from an interrupt handler, which might possibly result in entering
  * idle mode, in other words, leaving the mode in which read-side critical
- * sections can occur.
+ * sections can occur.  The caller must have disabled interrupts.
  *
  * This code assumes that the idle loop never does anything that might
  * result in unbalanced calls to irq_enter() and irq_exit().  If your
@@ -753,11 +745,10 @@ void rcu_user_enter(void)
  */
 void rcu_irq_exit(void)
 {
-	unsigned long flags;
 	long long oldval;
 	struct rcu_dynticks *rdtp;
 
-	local_irq_save(flags);
+	RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!");
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	rdtp->dynticks_nesting--;
@@ -768,6 +759,17 @@ void rcu_irq_exit(void)
 	else
 		rcu_eqs_enter_common(oldval, true);
 	rcu_sysidle_enter(1);
+}
+
+/*
+ * Wrapper for rcu_irq_exit() where interrupts are enabled.
+ */
+void rcu_irq_exit_irqson(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	rcu_irq_exit();
 	local_irq_restore(flags);
 }
 
@@ -865,7 +867,7 @@ void rcu_user_exit(void)
  *
  * Enter an interrupt handler, which might possibly result in exiting
  * idle mode, in other words, entering the mode in which read-side critical
- * sections can occur.
+ * sections can occur.  The caller must have disabled interrupts.
  *
  * Note that the Linux kernel is fully capable of entering an interrupt
  * handler that it never exits, for example when doing upcalls to
@@ -881,11 +883,10 @@ void rcu_user_exit(void)
  */
 void rcu_irq_enter(void)
 {
-	unsigned long flags;
 	struct rcu_dynticks *rdtp;
 	long long oldval;
 
-	local_irq_save(flags);
+	RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_enter() invoked with irqs enabled!!!");
 	rdtp = this_cpu_ptr(&rcu_dynticks);
 	oldval = rdtp->dynticks_nesting;
 	rdtp->dynticks_nesting++;
@@ -896,6 +897,17 @@ void rcu_irq_enter(void)
 	else
 		rcu_eqs_exit_common(oldval, true);
 	rcu_sysidle_exit(1);
+}
+
+/*
+ * Wrapper for rcu_irq_enter() where interrupts are enabled.
+ */
+void rcu_irq_enter_irqson(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	rcu_irq_enter();
 	local_irq_restore(flags);
 }
 
@@ -1187,6 +1199,16 @@ static void record_gp_stall_check_time(struct rcu_state *rsp)
 }
 
 /*
+ * Convert a ->gp_state value to a character string.
+ */
+static const char *gp_state_getname(short gs)
+{
+	if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names))
+		return "???";
+	return gp_state_names[gs];
+}
+
+/*
  * Complain about starvation of grace-period kthread.
  */
 static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
@@ -1196,12 +1218,16 @@ 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 s%d ->state=%#lx\n",
+	if (j - gpa > 2 * HZ) {
+		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->gp_state,
-		       rsp->gp_kthread ? rsp->gp_kthread->state : 0);
+		       rsp->gp_flags,
+		       gp_state_getname(rsp->gp_state), rsp->gp_state,
+		       rsp->gp_kthread ? rsp->gp_kthread->state : ~0);
+		if (rsp->gp_kthread)
+			sched_show_task(rsp->gp_kthread);
+	}
 }
 
 /*
@@ -1214,7 +1240,7 @@ static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
 	struct rcu_node *rnp;
 
 	rcu_for_each_leaf_node(rsp, rnp) {
-		raw_spin_lock_irqsave(&rnp->lock, flags);
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->qsmask != 0) {
 			for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
 				if (rnp->qsmask & (1UL << cpu))
@@ -1237,7 +1263,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 
 	/* Only let one CPU complain about others per time interval. */
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	delta = jiffies - READ_ONCE(rsp->jiffies_stall);
 	if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -1256,7 +1282,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 	       rsp->name);
 	print_cpu_stall_info_begin();
 	rcu_for_each_leaf_node(rsp, rnp) {
-		raw_spin_lock_irqsave(&rnp->lock, flags);
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		ndetected += rcu_print_task_stall(rnp);
 		if (rnp->qsmask != 0) {
 			for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++)
@@ -1327,7 +1353,7 @@ static void print_cpu_stall(struct rcu_state *rsp)
 
 	rcu_dump_cpu_stacks(rsp);
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
 		WRITE_ONCE(rsp->jiffies_stall,
 			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
@@ -1534,10 +1560,8 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 	 * hold it, acquire the root rcu_node structure's lock in order to
 	 * start one (if needed).
 	 */
-	if (rnp != rnp_root) {
-		raw_spin_lock(&rnp_root->lock);
-		smp_mb__after_unlock_lock();
-	}
+	if (rnp != rnp_root)
+		raw_spin_lock_rcu_node(rnp_root);
 
 	/*
 	 * Get a new grace-period number.  If there really is no grace
@@ -1786,11 +1810,10 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 	if ((rdp->gpnum == READ_ONCE(rnp->gpnum) &&
 	     rdp->completed == READ_ONCE(rnp->completed) &&
 	     !unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */
-	    !raw_spin_trylock(&rnp->lock)) { /* irqs already off, so later. */
+	    !raw_spin_trylock_rcu_node(rnp)) { /* irqs already off, so later. */
 		local_irq_restore(flags);
 		return;
 	}
-	smp_mb__after_unlock_lock();
 	needwake = __note_gp_changes(rsp, rnp, rdp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	if (needwake)
@@ -1805,21 +1828,20 @@ static void rcu_gp_slow(struct rcu_state *rsp, int delay)
 }
 
 /*
- * Initialize a new grace period.  Return 0 if no grace period required.
+ * Initialize a new grace period.  Return false if no grace period required.
  */
-static int rcu_gp_init(struct rcu_state *rsp)
+static bool rcu_gp_init(struct rcu_state *rsp)
 {
 	unsigned long oldmask;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	WRITE_ONCE(rsp->gp_activity, jiffies);
-	raw_spin_lock_irq(&rnp->lock);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irq_rcu_node(rnp);
 	if (!READ_ONCE(rsp->gp_flags)) {
 		/* Spurious wakeup, tell caller to go back to sleep.  */
 		raw_spin_unlock_irq(&rnp->lock);
-		return 0;
+		return false;
 	}
 	WRITE_ONCE(rsp->gp_flags, 0); /* Clear all flags: New grace period. */
 
@@ -1829,7 +1851,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 		 * Not supposed to be able to happen.
 		 */
 		raw_spin_unlock_irq(&rnp->lock);
-		return 0;
+		return false;
 	}
 
 	/* Advance to a new grace period and initialize state. */
@@ -1847,8 +1869,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	 */
 	rcu_for_each_leaf_node(rsp, rnp) {
 		rcu_gp_slow(rsp, gp_preinit_delay);
-		raw_spin_lock_irq(&rnp->lock);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irq_rcu_node(rnp);
 		if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
 		    !rnp->wait_blkd_tasks) {
 			/* Nothing to do on this leaf rcu_node structure. */
@@ -1904,8 +1925,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		rcu_gp_slow(rsp, gp_init_delay);
-		raw_spin_lock_irq(&rnp->lock);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irq_rcu_node(rnp);
 		rdp = this_cpu_ptr(rsp->rda);
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
@@ -1923,7 +1943,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 		WRITE_ONCE(rsp->gp_activity, jiffies);
 	}
 
-	return 1;
+	return true;
 }
 
 /*
@@ -1973,8 +1993,7 @@ static void rcu_gp_fqs(struct rcu_state *rsp, bool first_time)
 	}
 	/* Clear flag to prevent immediate re-entry. */
 	if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
-		raw_spin_lock_irq(&rnp->lock);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irq_rcu_node(rnp);
 		WRITE_ONCE(rsp->gp_flags,
 			   READ_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS);
 		raw_spin_unlock_irq(&rnp->lock);
@@ -1993,8 +2012,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	WRITE_ONCE(rsp->gp_activity, jiffies);
-	raw_spin_lock_irq(&rnp->lock);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irq_rcu_node(rnp);
 	gp_duration = jiffies - rsp->gp_start;
 	if (gp_duration > rsp->gp_max)
 		rsp->gp_max = gp_duration;
@@ -2019,8 +2037,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	 * grace period is recorded in any of the rcu_node structures.
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
-		raw_spin_lock_irq(&rnp->lock);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irq_rcu_node(rnp);
 		WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
 		WARN_ON_ONCE(rnp->qsmask);
 		WRITE_ONCE(rnp->completed, rsp->gpnum);
@@ -2035,8 +2052,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 		rcu_gp_slow(rsp, gp_cleanup_delay);
 	}
 	rnp = rcu_get_root(rsp);
-	raw_spin_lock_irq(&rnp->lock);
-	smp_mb__after_unlock_lock(); /* Order GP before ->completed update. */
+	raw_spin_lock_irq_rcu_node(rnp); /* Order GP before ->completed update. */
 	rcu_nocb_gp_set(rnp, nocb);
 
 	/* Declare grace period done. */
@@ -2284,8 +2300,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		rnp_c = rnp;
 		rnp = rnp->parent;
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		oldmask = rnp_c->qsmask;
 	}
 
@@ -2332,8 +2347,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
 	gps = rnp->gpnum;
 	mask = rnp->grpmask;
 	raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */
-	raw_spin_lock(&rnp_p->lock);	/* irqs already disabled. */
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_rcu_node(rnp_p);	/* irqs already disabled. */
 	rcu_report_qs_rnp(mask, rsp, rnp_p, gps, flags);
 }
 
@@ -2355,8 +2369,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 	struct rcu_node *rnp;
 
 	rnp = rdp->mynode;
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	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 ||
@@ -2582,8 +2595,7 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 		rnp = rnp->parent;
 		if (!rnp)
 			break;
-		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
-		smp_mb__after_unlock_lock(); /* GP memory ordering. */
+		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
 		rnp->qsmaskinit &= ~mask;
 		rnp->qsmask &= ~mask;
 		if (rnp->qsmaskinit) {
@@ -2611,8 +2623,7 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
 
 	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
 	mask = rdp->grpmask;
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();	/* Enforce GP memory-order guarantee. */
+	raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
 	rnp->qsmaskinitnext &= ~mask;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
@@ -2809,8 +2820,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
 	rcu_for_each_leaf_node(rsp, rnp) {
 		cond_resched_rcu_qs();
 		mask = 0;
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->qsmask == 0) {
 			if (rcu_state_p == &rcu_sched_state ||
 			    rsp != rcu_state_p ||
@@ -2881,8 +2891,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
 	/* rnp_old == rcu_get_root(rsp), rnp == NULL. */
 
 	/* Reached the root of the rcu_node tree, acquire lock. */
-	raw_spin_lock_irqsave(&rnp_old->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp_old, flags);
 	raw_spin_unlock(&rnp_old->fqslock);
 	if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		rsp->n_force_qs_lh++;
@@ -2914,7 +2923,7 @@ __rcu_process_callbacks(struct rcu_state *rsp)
 	/* Does this CPU require a not-yet-started grace period? */
 	local_irq_save(flags);
 	if (cpu_needs_another_gp(rsp, rdp)) {
-		raw_spin_lock(&rcu_get_root(rsp)->lock); /* irqs disabled. */
+		raw_spin_lock_rcu_node(rcu_get_root(rsp)); /* irqs disabled. */
 		needwake = rcu_start_gp(rsp);
 		raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags);
 		if (needwake)
@@ -3005,8 +3014,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 		if (!rcu_gp_in_progress(rsp)) {
 			struct rcu_node *rnp_root = rcu_get_root(rsp);
 
-			raw_spin_lock(&rnp_root->lock);
-			smp_mb__after_unlock_lock();
+			raw_spin_lock_rcu_node(rnp_root);
 			needwake = rcu_start_gp(rsp);
 			raw_spin_unlock(&rnp_root->lock);
 			if (needwake)
@@ -3365,7 +3373,6 @@ 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;
@@ -3392,6 +3399,7 @@ static void rcu_exp_gp_seq_end(struct rcu_state *rsp)
 }
 static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp)
 {
+	smp_mb(); /* Caller's modifications seen first by other CPUs. */
 	return rcu_seq_snap(&rsp->expedited_sequence);
 }
 static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s)
@@ -3426,8 +3434,7 @@ static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp)
 	 * 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();
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->expmaskinit == rnp->expmaskinitnext) {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 			continue;  /* No new CPUs, nothing to do. */
@@ -3447,8 +3454,7 @@ static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp)
 		rnp_up = rnp->parent;
 		done = false;
 		while (rnp_up) {
-			raw_spin_lock_irqsave(&rnp_up->lock, flags);
-			smp_mb__after_unlock_lock();
+			raw_spin_lock_irqsave_rcu_node(rnp_up, flags);
 			if (rnp_up->expmaskinit)
 				done = true;
 			rnp_up->expmaskinit |= mask;
@@ -3472,8 +3478,7 @@ static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp)
 
 	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();
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		WARN_ON_ONCE(rnp->expmask);
 		rnp->expmask = rnp->expmaskinit;
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -3531,8 +3536,7 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 		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();
+		raw_spin_lock_rcu_node(rnp); /* irqs already disabled */
 		WARN_ON_ONCE(!(rnp->expmask & mask));
 		rnp->expmask &= ~mask;
 	}
@@ -3549,8 +3553,7 @@ static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp,
 {
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	__rcu_report_exp_rnp(rsp, rnp, wake, flags);
 }
 
@@ -3564,8 +3567,7 @@ static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp,
 {
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	if (!(rnp->expmask & mask)) {
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
@@ -3609,7 +3611,7 @@ static bool sync_exp_work_done(struct rcu_state *rsp, struct rcu_node *rnp,
  */
 static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
 {
-	struct rcu_data *rdp;
+	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id());
 	struct rcu_node *rnp0;
 	struct rcu_node *rnp1 = NULL;
 
@@ -3623,7 +3625,7 @@ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
 	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))
+					       &rdp->expedited_workdone0, s))
 				return NULL;
 			return rnp0;
 		}
@@ -3637,14 +3639,13 @@ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
 	 * 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))
+	if (sync_exp_work_done(rsp, NULL, NULL, &rdp->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))
+				       &rdp->expedited_workdone2, s))
 			return NULL;
 		mutex_lock(&rnp0->exp_funnel_mutex);
 		if (rnp1)
@@ -3654,7 +3655,7 @@ static struct rcu_node *exp_funnel_lock(struct rcu_state *rsp, unsigned long s)
 		rnp1 = rnp0;
 	}
 	if (sync_exp_work_done(rsp, rnp1, rdp,
-			       &rsp->expedited_workdone3, s))
+			       &rdp->expedited_workdone3, s))
 		return NULL;
 	return rnp1;
 }
@@ -3708,8 +3709,7 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 
 	sync_exp_reset_tree(rsp);
 	rcu_for_each_leaf_node(rsp, rnp) {
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 
 		/* Each pass checks a CPU for identity, offline, and idle. */
 		mask_ofl_test = 0;
@@ -3741,24 +3741,22 @@ 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;
+				continue;
+			}
+			/* Failed, raced with offline. */
+			raw_spin_lock_irqsave_rcu_node(rnp, 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_rcu_node(rnp, 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;
@@ -3773,6 +3771,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 	unsigned long jiffies_stall;
 	unsigned long jiffies_start;
 	unsigned long mask;
+	int ndetected;
 	struct rcu_node *rnp;
 	struct rcu_node *rnp_root = rcu_get_root(rsp);
 	int ret;
@@ -3785,7 +3784,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 				rsp->expedited_wq,
 				sync_rcu_preempt_exp_done(rnp_root),
 				jiffies_stall);
-		if (ret > 0)
+		if (ret > 0 || sync_rcu_preempt_exp_done(rnp_root))
 			return;
 		if (ret < 0) {
 			/* Hit a signal, disable CPU stall warnings. */
@@ -3795,14 +3794,16 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 		}
 		pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {",
 		       rsp->name);
+		ndetected = 0;
 		rcu_for_each_leaf_node(rsp, rnp) {
-			(void)rcu_print_task_exp_stall(rnp);
+			ndetected = 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;
+				ndetected++;
 				rdp = per_cpu_ptr(rsp->rda, cpu);
 				pr_cont(" %d-%c%c%c", cpu,
 					"O."[cpu_online(cpu)],
@@ -3811,8 +3812,23 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 			}
 			mask <<= 1;
 		}
-		pr_cont(" } %lu jiffies s: %lu\n",
-			jiffies - jiffies_start, rsp->expedited_sequence);
+		pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n",
+			jiffies - jiffies_start, rsp->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) {
+				if (rnp == rnp_root)
+					continue; /* printed unconditionally */
+				if (sync_rcu_preempt_exp_done(rnp))
+					continue;
+				pr_cont(" l=%u:%d-%d:%#lx/%c",
+					rnp->level, rnp->grplo, rnp->grphi,
+					rnp->expmask,
+					".T"[!!rnp->exp_tasks]);
+			}
+			pr_cont("\n");
+		}
 		rcu_for_each_leaf_node(rsp, rnp) {
 			mask = 1;
 			for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask <<= 1) {
@@ -3847,6 +3863,16 @@ void synchronize_sched_expedited(void)
 	struct rcu_node *rnp;
 	struct rcu_state *rsp = &rcu_sched_state;
 
+	/* If only one CPU, this is automatically a grace period. */
+	if (rcu_blocking_is_gp())
+		return;
+
+	/* If expedited grace periods are prohibited, fall back to normal. */
+	if (rcu_gp_is_normal()) {
+		wait_rcu_gp(call_rcu_sched);
+		return;
+	}
+
 	/* Take a snapshot of the sequence number.  */
 	s = rcu_exp_gp_seq_snap(rsp);
 
@@ -4135,7 +4161,7 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
 		rnp = rnp->parent;
 		if (rnp == NULL)
 			return;
-		raw_spin_lock(&rnp->lock); /* Interrupts already disabled. */
+		raw_spin_lock_rcu_node(rnp); /* Interrupts already disabled. */
 		rnp->qsmaskinit |= mask;
 		raw_spin_unlock(&rnp->lock); /* Interrupts remain disabled. */
 	}
@@ -4152,7 +4178,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	/* Set up local state, ensuring consistent view of global state. */
-	raw_spin_lock_irqsave(&rnp->lock, flags);
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo);
 	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
 	WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE);
@@ -4179,7 +4205,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	/* Set up local state, ensuring consistent view of global state. */
-	raw_spin_lock_irqsave(&rnp->lock, flags);
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	rdp->qlen_last_fqs_check = 0;
 	rdp->n_force_qs_snap = rsp->n_force_qs;
 	rdp->blimit = blimit;
@@ -4198,8 +4224,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	 */
 	rnp = rdp->mynode;
 	mask = rdp->grpmask;
-	raw_spin_lock(&rnp->lock);		/* irqs already disabled. */
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_rcu_node(rnp);		/* irqs already disabled. */
 	rnp->qsmaskinitnext |= mask;
 	rnp->expmaskinitnext |= mask;
 	if (!rdp->beenonline)
@@ -4327,14 +4352,14 @@ static int __init rcu_spawn_gp_kthread(void)
 		t = kthread_create(rcu_gp_kthread, rsp, "%s", rsp->name);
 		BUG_ON(IS_ERR(t));
 		rnp = rcu_get_root(rsp);
-		raw_spin_lock_irqsave(&rnp->lock, flags);
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		rsp->gp_kthread = t;
 		if (kthread_prio) {
 			sp.sched_priority = kthread_prio;
 			sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
 		}
-		wake_up_process(t);
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+		wake_up_process(t);
 	}
 	rcu_spawn_nocb_kthreads();
 	rcu_spawn_boost_kthreads();
@@ -4385,12 +4410,14 @@ static void __init rcu_init_levelspread(int *levelspread, const int *levelcnt)
 /*
  * Helper function for rcu_init() that initializes one rcu_state structure.
  */
-static void __init rcu_init_one(struct rcu_state *rsp,
-		struct rcu_data __percpu *rda)
+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 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 u8 fl_mask = 0x1;
 
 	int levelcnt[RCU_NUM_LVLS];		/* # nodes in each level. */
@@ -4576,8 +4603,8 @@ void __init rcu_init(void)
 
 	rcu_bootup_announce();
 	rcu_init_geometry();
-	rcu_init_one(&rcu_bh_state, &rcu_bh_data);
-	rcu_init_one(&rcu_sched_state, &rcu_sched_data);
+	rcu_init_one(&rcu_bh_state);
+	rcu_init_one(&rcu_sched_state);
 	if (dump_tree)
 		rcu_dump_rcu_node_tree(&rcu_sched_state);
 	__rcu_init_preempt();
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 9fb4e238d4dc..83360b4f4352 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -178,6 +178,8 @@ struct rcu_node {
 				/*  beginning of each expedited GP. */
 	unsigned long expmaskinitnext;
 				/* Online CPUs for next expedited GP. */
+				/*  Any CPU that has ever been online will */
+				/*  have its bit set. */
 	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. */
@@ -384,6 +386,10 @@ struct rcu_data {
 	struct rcu_head oom_head;
 #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
 	struct mutex exp_funnel_mutex;
+	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. */
 
 	/* 7) Callback offloading. */
 #ifdef CONFIG_RCU_NOCB_CPU
@@ -498,10 +504,6 @@ struct rcu_state {
 	/* End of fields guarded by barrier_mutex. */
 
 	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_t expedited_need_qs;		/* # CPUs left to check in. */
 	wait_queue_head_t expedited_wq;		/* Wait for check-ins. */
@@ -545,6 +547,18 @@ struct rcu_state {
 #define RCU_GP_CLEANUP   5	/* Grace-period cleanup started. */
 #define RCU_GP_CLEANED   6	/* Grace-period cleanup complete. */
 
+#ifndef RCU_TREE_NONCORE
+static const char * const gp_state_names[] = {
+	"RCU_GP_IDLE",
+	"RCU_GP_WAIT_GPS",
+	"RCU_GP_DONE_GPS",
+	"RCU_GP_WAIT_FQS",
+	"RCU_GP_DOING_FQS",
+	"RCU_GP_CLEANUP",
+	"RCU_GP_CLEANED",
+};
+#endif /* #ifndef RCU_TREE_NONCORE */
+
 extern struct list_head rcu_struct_flavors;
 
 /* Sequence through rcu_state structures for each RCU flavor. */
@@ -664,3 +678,42 @@ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
 #else /* #ifdef CONFIG_PPC */
 #define smp_mb__after_unlock_lock()	do { } while (0)
 #endif /* #else #ifdef CONFIG_PPC */
+
+/*
+ * Wrappers for the rcu_node::lock acquire.
+ *
+ * Because the rcu_nodes form a tree, the tree traversal locking will observe
+ * different lock values, this in turn means that an UNLOCK of one level
+ * followed by a LOCK of another level does not imply a full memory barrier;
+ * and most importantly transitivity is lost.
+ *
+ * In order to restore full ordering between tree levels, augment the regular
+ * lock acquire functions with smp_mb__after_unlock_lock().
+ */
+static inline void raw_spin_lock_rcu_node(struct rcu_node *rnp)
+{
+	raw_spin_lock(&rnp->lock);
+	smp_mb__after_unlock_lock();
+}
+
+static inline void raw_spin_lock_irq_rcu_node(struct rcu_node *rnp)
+{
+	raw_spin_lock_irq(&rnp->lock);
+	smp_mb__after_unlock_lock();
+}
+
+#define raw_spin_lock_irqsave_rcu_node(rnp, flags)	\
+do {							\
+	typecheck(unsigned long, flags);		\
+	raw_spin_lock_irqsave(&(rnp)->lock, flags);	\
+	smp_mb__after_unlock_lock();			\
+} while (0)
+
+static inline bool raw_spin_trylock_rcu_node(struct rcu_node *rnp)
+{
+	bool locked = raw_spin_trylock(&rnp->lock);
+
+	if (locked)
+		smp_mb__after_unlock_lock();
+	return locked;
+}
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 630c19772630..9467a8b7e756 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -63,8 +63,7 @@ static bool __read_mostly rcu_nocb_poll;    /* Offload kthread are to poll. */
 
 /*
  * Check the RCU kernel configuration parameters and print informative
- * messages about anything out of the ordinary.  If you like #ifdef, you
- * will love this function.
+ * messages about anything out of the ordinary.
  */
 static void __init rcu_bootup_announce_oddness(void)
 {
@@ -147,8 +146,8 @@ static void __init rcu_bootup_announce(void)
  * 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)
+static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
+	__releases(rnp->lock) /* But leaves rrupts disabled. */
 {
 	int blkd_state = (rnp->gp_tasks ? RCU_GP_TASKS : 0) +
 			 (rnp->exp_tasks ? RCU_EXP_TASKS : 0) +
@@ -236,7 +235,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp,
 		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);
+	raw_spin_unlock(&rnp->lock); /* rrupts remain disabled. */
 
 	/*
 	 * Report the quiescent state for the expedited GP.  This expedited
@@ -251,7 +250,6 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp,
 	} else {
 		WARN_ON_ONCE(t->rcu_read_unlock_special.b.exp_need_qs);
 	}
-	local_irq_restore(flags);
 }
 
 /*
@@ -286,12 +284,11 @@ static void rcu_preempt_qs(void)
  * predating the current grace period drain, in other words, until
  * rnp->gp_tasks becomes NULL.
  *
- * Caller must disable preemption.
+ * Caller must disable interrupts.
  */
 static void rcu_preempt_note_context_switch(void)
 {
 	struct task_struct *t = current;
-	unsigned long flags;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 
@@ -301,8 +298,7 @@ static void rcu_preempt_note_context_switch(void)
 		/* Possibly blocking in an RCU read-side critical section. */
 		rdp = this_cpu_ptr(rcu_state_p->rda);
 		rnp = rdp->mynode;
-		raw_spin_lock_irqsave(&rnp->lock, flags);
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_rcu_node(rnp);
 		t->rcu_read_unlock_special.b.blocked = true;
 		t->rcu_blocked_node = rnp;
 
@@ -318,7 +314,7 @@ static void rcu_preempt_note_context_switch(void)
 				       (rnp->qsmask & rdp->grpmask)
 				       ? rnp->gpnum
 				       : rnp->gpnum + 1);
-		rcu_preempt_ctxt_queue(rnp, rdp, flags);
+		rcu_preempt_ctxt_queue(rnp, rdp);
 	} else if (t->rcu_read_lock_nesting < 0 &&
 		   t->rcu_read_unlock_special.s) {
 
@@ -450,20 +446,13 @@ void rcu_read_unlock_special(struct task_struct *t)
 
 		/*
 		 * Remove this task from the list it blocked on.  The task
-		 * now remains queued on the rcu_node corresponding to
-		 * the CPU it first blocked on, so the first attempt to
-		 * acquire the task's rcu_node's ->lock will succeed.
-		 * Keep the loop and add a WARN_ON() out of sheer paranoia.
+		 * now remains queued on the rcu_node corresponding to the
+		 * CPU it first blocked on, so there is no longer any need
+		 * to loop.  Retain a WARN_ON_ONCE() out of sheer paranoia.
 		 */
-		for (;;) {
-			rnp = t->rcu_blocked_node;
-			raw_spin_lock(&rnp->lock);  /* irqs already disabled. */
-			smp_mb__after_unlock_lock();
-			if (rnp == t->rcu_blocked_node)
-				break;
-			WARN_ON_ONCE(1);
-			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
-		}
+		rnp = t->rcu_blocked_node;
+		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
+		WARN_ON_ONCE(rnp != t->rcu_blocked_node);
 		empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
 		empty_exp = sync_rcu_preempt_exp_done(rnp);
 		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
@@ -527,7 +516,7 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
 	unsigned long flags;
 	struct task_struct *t;
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	if (!rcu_preempt_blocked_readers_cgp(rnp)) {
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 		return;
@@ -748,6 +737,12 @@ void synchronize_rcu_expedited(void)
 	struct rcu_state *rsp = rcu_state_p;
 	unsigned long s;
 
+	/* If expedited grace periods are prohibited, fall back to normal. */
+	if (rcu_gp_is_normal()) {
+		wait_rcu_gp(call_rcu);
+		return;
+	}
+
 	s = rcu_exp_gp_seq_snap(rsp);
 
 	rnp_unlock = exp_funnel_lock(rsp, s);
@@ -788,7 +783,7 @@ EXPORT_SYMBOL_GPL(rcu_barrier);
  */
 static void __init __rcu_init_preempt(void)
 {
-	rcu_init_one(rcu_state_p, rcu_data_p);
+	rcu_init_one(rcu_state_p);
 }
 
 /*
@@ -989,8 +984,7 @@ static int rcu_boost(struct rcu_node *rnp)
 	    READ_ONCE(rnp->boost_tasks) == NULL)
 		return 0;  /* Nothing left to boost. */
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 
 	/*
 	 * Recheck under the lock: all tasks in need of boosting
@@ -1176,8 +1170,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 			   "rcub/%d", rnp_index);
 	if (IS_ERR(t))
 		return PTR_ERR(t);
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	rnp->boost_kthread_task = t;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	sp.sched_priority = kthread_prio;
@@ -1524,7 +1517,8 @@ static void rcu_prepare_for_idle(void)
 	struct rcu_state *rsp;
 	int tne;
 
-	if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL))
+	if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) ||
+	    rcu_is_nocb_cpu(smp_processor_id()))
 		return;
 
 	/* Handle nohz enablement switches conservatively. */
@@ -1538,10 +1532,6 @@ static void rcu_prepare_for_idle(void)
 	if (!tne)
 		return;
 
-	/* If this is a no-CBs CPU, no callbacks, just return. */
-	if (rcu_is_nocb_cpu(smp_processor_id()))
-		return;
-
 	/*
 	 * If a non-lazy callback arrived at a CPU having only lazy
 	 * callbacks, invoke RCU core for the side-effect of recalculating
@@ -1567,8 +1557,7 @@ static void rcu_prepare_for_idle(void)
 		if (!*rdp->nxttail[RCU_DONE_TAIL])
 			continue;
 		rnp = rdp->mynode;
-		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
-		smp_mb__after_unlock_lock();
+		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
 		needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
 		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 		if (needwake)
@@ -2068,8 +2057,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	bool needwake;
 	struct rcu_node *rnp = rdp->mynode;
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
-	smp_mb__after_unlock_lock();
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	needwake = rcu_start_future_gp(rnp, rdp, &c);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	if (needwake)
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index ef7093cc9b5c..1088e64f01ad 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -1,5 +1,5 @@
 /*
- * Read-Copy Update tracing for classic implementation
+ * Read-Copy Update tracing for hierarchical implementation.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -16,6 +16,7 @@
  * http://www.gnu.org/licenses/gpl-2.0.html.
  *
  * Copyright IBM Corporation, 2008
+ * Author: Paul E. McKenney
  *
  * Papers:  http://www.rdrop.com/users/paulmck/RCU
  *
@@ -33,9 +34,7 @@
 #include <linux/sched.h>
 #include <linux/atomic.h>
 #include <linux/bitops.h>
-#include <linux/module.h>
 #include <linux/completion.h>
-#include <linux/moduleparam.h>
 #include <linux/percpu.h>
 #include <linux/notifier.h>
 #include <linux/cpu.h>
@@ -183,14 +182,20 @@ static const struct file_operations rcudata_fops = {
 
 static int show_rcuexp(struct seq_file *m, void *v)
 {
+	int cpu;
 	struct rcu_state *rsp = (struct rcu_state *)m->private;
-
+	struct rcu_data *rdp;
+	unsigned long s0 = 0, s1 = 0, s2 = 0, s3 = 0;
+
+	for_each_possible_cpu(cpu) {
+		rdp = per_cpu_ptr(rsp->rda, cpu);
+		s0 += atomic_long_read(&rdp->expedited_workdone0);
+		s1 += atomic_long_read(&rdp->expedited_workdone1);
+		s2 += atomic_long_read(&rdp->expedited_workdone2);
+		s3 += atomic_long_read(&rdp->expedited_workdone3);
+	}
 	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),
+		   rsp->expedited_sequence, s0, s1, s2, s3,
 		   atomic_long_read(&rsp->expedited_normal),
 		   atomic_read(&rsp->expedited_need_qs),
 		   rsp->expedited_sequence / 2);
@@ -319,7 +324,7 @@ static void show_one_rcugp(struct seq_file *m, struct rcu_state *rsp)
 	unsigned long gpmax;
 	struct rcu_node *rnp = &rsp->node[0];
 
-	raw_spin_lock_irqsave(&rnp->lock, flags);
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	completed = READ_ONCE(rsp->completed);
 	gpnum = READ_ONCE(rsp->gpnum);
 	if (completed == gpnum)
@@ -487,16 +492,4 @@ free_out:
 	debugfs_remove_recursive(rcudir);
 	return 1;
 }
-
-static void __exit rcutree_trace_cleanup(void)
-{
-	debugfs_remove_recursive(rcudir);
-}
-
-
-module_init(rcutree_trace_init);
-module_exit(rcutree_trace_cleanup);
-
-MODULE_AUTHOR("Paul E. McKenney");
-MODULE_DESCRIPTION("Read-Copy Update tracing for hierarchical implementation");
-MODULE_LICENSE("GPL");
+device_initcall(rcutree_trace_init);
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 5f748c5a40f0..76b94e19430b 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -60,7 +60,12 @@ MODULE_ALIAS("rcupdate");
 #endif
 #define MODULE_PARAM_PREFIX "rcupdate."
 
+#ifndef CONFIG_TINY_RCU
 module_param(rcu_expedited, int, 0);
+module_param(rcu_normal, int, 0);
+static int rcu_normal_after_boot;
+module_param(rcu_normal_after_boot, int, 0);
+#endif /* #ifndef CONFIG_TINY_RCU */
 
 #if defined(CONFIG_DEBUG_LOCK_ALLOC) && defined(CONFIG_PREEMPT_COUNT)
 /**
@@ -113,6 +118,17 @@ EXPORT_SYMBOL(rcu_read_lock_sched_held);
 
 #ifndef CONFIG_TINY_RCU
 
+/*
+ * Should expedited grace-period primitives always fall back to their
+ * non-expedited counterparts?  Intended for use within RCU.  Note
+ * that if the user specifies both rcu_expedited and rcu_normal, then
+ * rcu_normal wins.
+ */
+bool rcu_gp_is_normal(void)
+{
+	return READ_ONCE(rcu_normal);
+}
+
 static atomic_t rcu_expedited_nesting =
 	ATOMIC_INIT(IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT) ? 1 : 0);
 
@@ -157,8 +173,6 @@ void rcu_unexpedite_gp(void)
 }
 EXPORT_SYMBOL_GPL(rcu_unexpedite_gp);
 
-#endif /* #ifndef CONFIG_TINY_RCU */
-
 /*
  * Inform RCU of the end of the in-kernel boot sequence.
  */
@@ -166,8 +180,12 @@ void rcu_end_inkernel_boot(void)
 {
 	if (IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT))
 		rcu_unexpedite_gp();
+	if (rcu_normal_after_boot)
+		WRITE_ONCE(rcu_normal, 1);
 }
 
+#endif /* #ifndef CONFIG_TINY_RCU */
+
 #ifdef CONFIG_PREEMPT_RCU
 
 /*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 732e993b564b..1ef0d7aeab47 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3109,7 +3109,6 @@ static void __sched notrace __schedule(bool preempt)
 
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
-	rcu_note_context_switch();
 	prev = rq->curr;
 
 	/*
@@ -3128,13 +3127,16 @@ static void __sched notrace __schedule(bool preempt)
 	if (sched_feat(HRTICK))
 		hrtick_clear(rq);
 
+	local_irq_disable();
+	rcu_note_context_switch();
+
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
 	 * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
 	 * done by the caller to avoid the race with signal_wake_up().
 	 */
 	smp_mb__before_spinlock();
-	raw_spin_lock_irq(&rq->lock);
+	raw_spin_lock(&rq->lock);
 	lockdep_pin_lock(&rq->lock);
 
 	rq->clock_skip_update <<= 1; /* promote REQ to ACT */