Merge tag 'rcu.2022.01.09a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu

Pull RCU updates from Paul McKenney:

 - Documentation updates, perhaps most notably Neil Brown's writeup of
   the reference-counting analogy to RCU.

 - Expedited grace-period cleanups.

 - Remove CONFIG_RCU_FAST_NO_HZ due to lack of valid users. I have asked
   around, posted a blog entry, and sent this series to LKML without
   result.

 - Miscellaneous fixes.

 - RCU callback offloading updates, perhaps most notably Frederic
   Weisbecker's updates allowing CPUs booted in the de-offloaded state
   to be offloaded at runtime.

 - nolibc fixes from Willy Tarreau and Anmar Faizi, but also including
   Mark Brown's addition of gettid().

 - RCU Tasks Trace fixes, including changes that increase the
   scalability of call_rcu_tasks_trace() for the BPF folks (Martin Lau
   and KP Singh).

 - Various fixes including those from Wander Lairson Costa and Li
   Zhijian.

 - Fixes plus addition of tests for the increased call_rcu_tasks_trace()
   scalability.

* tag 'rcu.2022.01.09a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu: (87 commits)
  rcu/nocb: Merge rcu_spawn_cpu_nocb_kthread() and rcu_spawn_one_nocb_kthread()
  rcu/nocb: Allow empty "rcu_nocbs" kernel parameter
  rcu/nocb: Create kthreads on all CPUs if "rcu_nocbs=" or "nohz_full=" are passed
  rcu/nocb: Optimize kthreads and rdp initialization
  rcu/nocb: Prepare nocb_cb_wait() to start with a non-offloaded rdp
  rcu/nocb: Remove rcu_node structure from nocb list when de-offloaded
  rcu-tasks: Use fewer callbacks queues if callback flood ends
  rcu-tasks: Use separate ->percpu_dequeue_lim for callback dequeueing
  rcu-tasks: Use more callback queues if contention encountered
  rcu-tasks: Avoid raw-spinlocked wakeups from call_rcu_tasks_generic()
  rcu-tasks: Count trylocks to estimate call_rcu_tasks() contention
  rcu-tasks: Add rcupdate.rcu_task_enqueue_lim to set initial queueing
  rcu-tasks: Make rcu_barrier_tasks*() handle multiple callback queues
  rcu-tasks: Use workqueues for multiple rcu_tasks_invoke_cbs() invocations
  rcu-tasks: Abstract invocations of callbacks
  rcu-tasks: Abstract checking of callback lists
  rcu-tasks: Add a ->percpu_enqueue_lim to the rcu_tasks structure
  rcu-tasks: Inspect stalled task's trc state in locked state
  rcu-tasks: Use spin_lock_rcu_node() and friends
  rcutorture: Combine n_max_cbs from all kthreads in a callback flood
  ...

17 files changed, 873 insertions, 582 deletions

diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 397ac13d2ef7..9c2fb613a55d 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -1047,7 +1047,7 @@ static int __init lock_torture_init(void)
 				       sizeof(writer_tasks[0]),
 				       GFP_KERNEL);
 		if (writer_tasks == NULL) {
-			VERBOSE_TOROUT_ERRSTRING("writer_tasks: Out of memory");
+			TOROUT_ERRSTRING("writer_tasks: Out of memory");
 			firsterr = -ENOMEM;
 			goto unwind;
 		}
@@ -1058,7 +1058,7 @@ static int __init lock_torture_init(void)
 				       sizeof(reader_tasks[0]),
 				       GFP_KERNEL);
 		if (reader_tasks == NULL) {
-			VERBOSE_TOROUT_ERRSTRING("reader_tasks: Out of memory");
+			TOROUT_ERRSTRING("reader_tasks: Out of memory");
 			kfree(writer_tasks);
 			writer_tasks = NULL;
 			firsterr = -ENOMEM;
diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig
index 3128b7cf8e1f..bf8e341e75b4 100644
--- a/kernel/rcu/Kconfig
+++ b/kernel/rcu/Kconfig
@@ -112,7 +112,7 @@ config RCU_STALL_COMMON
 	  making these warnings mandatory for the tree variants.
 
 config RCU_NEED_SEGCBLIST
-	def_bool ( TREE_RCU || TREE_SRCU )
+	def_bool ( TREE_RCU || TREE_SRCU || TASKS_RCU_GENERIC )
 
 config RCU_FANOUT
 	int "Tree-based hierarchical RCU fanout value"
@@ -169,24 +169,6 @@ config RCU_FANOUT_LEAF
 
 	  Take the default if unsure.
 
-config RCU_FAST_NO_HZ
-	bool "Accelerate last non-dyntick-idle CPU's grace periods"
-	depends on NO_HZ_COMMON && SMP && RCU_EXPERT
-	default n
-	help
-	  This option permits CPUs to enter dynticks-idle state even if
-	  they have RCU callbacks queued, and prevents RCU from waking
-	  these CPUs up more than roughly once every four jiffies (by
-	  default, you can adjust this using the rcutree.rcu_idle_gp_delay
-	  parameter), thus improving energy efficiency.  On the other
-	  hand, this option increases the duration of RCU grace periods,
-	  for example, slowing down synchronize_rcu().
-
-	  Say Y if energy efficiency is critically important, and you
-	  	don't care about increased grace-period durations.
-
-	  Say N if you are unsure.
-
 config RCU_BOOST
 	bool "Enable RCU priority boosting"
 	depends on (RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT) || PREEMPT_RT
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index aaa111237b60..81145c3ece25 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/kernel/rcu/rcu_segcblist.c
@@ -261,16 +261,14 @@ void rcu_segcblist_disable(struct rcu_segcblist *rsclp)
 }
 
 /*
- * Mark the specified rcu_segcblist structure as offloaded.
+ * Mark the specified rcu_segcblist structure as offloaded (or not)
  */
 void rcu_segcblist_offload(struct rcu_segcblist *rsclp, bool offload)
 {
-	if (offload) {
-		rcu_segcblist_clear_flags(rsclp, SEGCBLIST_SOFTIRQ_ONLY);
-		rcu_segcblist_set_flags(rsclp, SEGCBLIST_OFFLOADED);
-	} else {
+	if (offload)
+		rcu_segcblist_set_flags(rsclp, SEGCBLIST_LOCKING | SEGCBLIST_OFFLOADED);
+	else
 		rcu_segcblist_clear_flags(rsclp, SEGCBLIST_OFFLOADED);
-	}
 }
 
 /*
diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h
index 9a19328ff251..e373fbe44da5 100644
--- a/kernel/rcu/rcu_segcblist.h
+++ b/kernel/rcu/rcu_segcblist.h
@@ -80,11 +80,14 @@ static inline bool rcu_segcblist_is_enabled(struct rcu_segcblist *rsclp)
 	return rcu_segcblist_test_flags(rsclp, SEGCBLIST_ENABLED);
 }
 
-/* Is the specified rcu_segcblist offloaded, or is SEGCBLIST_SOFTIRQ_ONLY set? */
+/*
+ * Is the specified rcu_segcblist NOCB offloaded (or in the middle of the
+ * [de]offloading process)?
+ */
 static inline bool rcu_segcblist_is_offloaded(struct rcu_segcblist *rsclp)
 {
 	if (IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
-	    !rcu_segcblist_test_flags(rsclp, SEGCBLIST_SOFTIRQ_ONLY))
+	    rcu_segcblist_test_flags(rsclp, SEGCBLIST_LOCKING))
 		return true;
 
 	return false;
@@ -92,9 +95,8 @@ static inline bool rcu_segcblist_is_offloaded(struct rcu_segcblist *rsclp)
 
 static inline bool rcu_segcblist_completely_offloaded(struct rcu_segcblist *rsclp)
 {
-	int flags = SEGCBLIST_KTHREAD_CB | SEGCBLIST_KTHREAD_GP | SEGCBLIST_OFFLOADED;
-
-	if (IS_ENABLED(CONFIG_RCU_NOCB_CPU) && (rsclp->flags & flags) == flags)
+	if (IS_ENABLED(CONFIG_RCU_NOCB_CPU) &&
+	    !rcu_segcblist_test_flags(rsclp, SEGCBLIST_RCU_CORE))
 		return true;
 
 	return false;
diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
index 228f143bf935..5e4f1f83d38e 100644
--- a/kernel/rcu/rcuscale.c
+++ b/kernel/rcu/rcuscale.c
@@ -50,8 +50,8 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com>");
 	pr_alert("%s" SCALE_FLAG " %s\n", scale_type, s)
 #define VERBOSE_SCALEOUT_STRING(s) \
 	do { if (verbose) pr_alert("%s" SCALE_FLAG " %s\n", scale_type, s); } while (0)
-#define VERBOSE_SCALEOUT_ERRSTRING(s) \
-	do { if (verbose) pr_alert("%s" SCALE_FLAG "!!! %s\n", scale_type, s); } while (0)
+#define SCALEOUT_ERRSTRING(s) \
+	pr_alert("%s" SCALE_FLAG "!!! %s\n", scale_type, s)
 
 /*
  * The intended use cases for the nreaders and nwriters module parameters
@@ -514,11 +514,11 @@ rcu_scale_cleanup(void)
 	 * during the mid-boot phase, so have to wait till the end.
 	 */
 	if (rcu_gp_is_expedited() && !rcu_gp_is_normal() && !gp_exp)
-		VERBOSE_SCALEOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!");
+		SCALEOUT_ERRSTRING("All grace periods expedited, no normal ones to measure!");
 	if (rcu_gp_is_normal() && gp_exp)
-		VERBOSE_SCALEOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!");
+		SCALEOUT_ERRSTRING("All grace periods normal, no expedited ones to measure!");
 	if (gp_exp && gp_async)
-		VERBOSE_SCALEOUT_ERRSTRING("No expedited async GPs, so went with async!");
+		SCALEOUT_ERRSTRING("No expedited async GPs, so went with async!");
 
 	if (torture_cleanup_begin())
 		return;
@@ -845,7 +845,7 @@ rcu_scale_init(void)
 	reader_tasks = kcalloc(nrealreaders, sizeof(reader_tasks[0]),
 			       GFP_KERNEL);
 	if (reader_tasks == NULL) {
-		VERBOSE_SCALEOUT_ERRSTRING("out of memory");
+		SCALEOUT_ERRSTRING("out of memory");
 		firsterr = -ENOMEM;
 		goto unwind;
 	}
@@ -865,7 +865,7 @@ rcu_scale_init(void)
 		kcalloc(nrealwriters, sizeof(*writer_n_durations),
 			GFP_KERNEL);
 	if (!writer_tasks || !writer_durations || !writer_n_durations) {
-		VERBOSE_SCALEOUT_ERRSTRING("out of memory");
+		SCALEOUT_ERRSTRING("out of memory");
 		firsterr = -ENOMEM;
 		goto unwind;
 	}
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 8b410d982990..33ea446101b3 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -46,6 +46,7 @@
 #include <linux/oom.h>
 #include <linux/tick.h>
 #include <linux/rcupdate_trace.h>
+#include <linux/nmi.h>
 
 #include "rcu.h"
 
@@ -53,15 +54,18 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@linux.ibm.com> and Josh Triplett <josh@joshtriplett.org>");
 
 /* Bits for ->extendables field, extendables param, and related definitions. */
-#define RCUTORTURE_RDR_SHIFT	 8	/* Put SRCU index in upper bits. */
-#define RCUTORTURE_RDR_MASK	 ((1 << RCUTORTURE_RDR_SHIFT) - 1)
+#define RCUTORTURE_RDR_SHIFT_1	 8	/* Put SRCU index in upper bits. */
+#define RCUTORTURE_RDR_MASK_1	 (1 << RCUTORTURE_RDR_SHIFT_1)
+#define RCUTORTURE_RDR_SHIFT_2	 9	/* Put SRCU index in upper bits. */
+#define RCUTORTURE_RDR_MASK_2	 (1 << RCUTORTURE_RDR_SHIFT_2)
 #define RCUTORTURE_RDR_BH	 0x01	/* Extend readers by disabling bh. */
 #define RCUTORTURE_RDR_IRQ	 0x02	/*  ... disabling interrupts. */
 #define RCUTORTURE_RDR_PREEMPT	 0x04	/*  ... disabling preemption. */
 #define RCUTORTURE_RDR_RBH	 0x08	/*  ... rcu_read_lock_bh(). */
 #define RCUTORTURE_RDR_SCHED	 0x10	/*  ... rcu_read_lock_sched(). */
-#define RCUTORTURE_RDR_RCU	 0x20	/*  ... entering another RCU reader. */
-#define RCUTORTURE_RDR_NBITS	 6	/* Number of bits defined above. */
+#define RCUTORTURE_RDR_RCU_1	 0x20	/*  ... entering another RCU reader. */
+#define RCUTORTURE_RDR_RCU_2	 0x40	/*  ... entering another RCU reader. */
+#define RCUTORTURE_RDR_NBITS	 7	/* Number of bits defined above. */
 #define RCUTORTURE_MAX_EXTEND	 \
 	(RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ | RCUTORTURE_RDR_PREEMPT | \
 	 RCUTORTURE_RDR_RBH | RCUTORTURE_RDR_SCHED)
@@ -75,7 +79,7 @@ torture_param(int, fqs_duration, 0,
 	      "Duration of fqs bursts (us), 0 to disable");
 torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)");
 torture_param(int, fqs_stutter, 3, "Wait time between fqs bursts (s)");
-torture_param(bool, fwd_progress, 1, "Test grace-period forward progress");
+torture_param(int, fwd_progress, 1, "Test grace-period forward progress");
 torture_param(int, fwd_progress_div, 4, "Fraction of CPU stall to wait");
 torture_param(int, fwd_progress_holdoff, 60,
 	      "Time between forward-progress tests (s)");
@@ -109,6 +113,8 @@ torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable.");
 torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable.");
 torture_param(int, stall_cpu_holdoff, 10,
 	     "Time to wait before starting stall (s).");
+torture_param(bool, stall_no_softlockup, false,
+	     "Avoid softlockup warning during cpu stall.");
 torture_param(int, stall_cpu_irqsoff, 0, "Disable interrupts while stalling.");
 torture_param(int, stall_cpu_block, 0, "Sleep while stalling.");
 torture_param(int, stall_gp_kthread, 0,
@@ -140,7 +146,7 @@ static struct task_struct *stats_task;
 static struct task_struct *fqs_task;
 static struct task_struct *boost_tasks[NR_CPUS];
 static struct task_struct *stall_task;
-static struct task_struct *fwd_prog_task;
+static struct task_struct **fwd_prog_tasks;
 static struct task_struct **barrier_cbs_tasks;
 static struct task_struct *barrier_task;
 static struct task_struct *read_exit_task;
@@ -342,10 +348,12 @@ struct rcu_torture_ops {
 	void (*gp_kthread_dbg)(void);
 	bool (*check_boost_failed)(unsigned long gp_state, int *cpup);
 	int (*stall_dur)(void);
+	long cbflood_max;
 	int irq_capable;
 	int can_boost;
 	int extendables;
 	int slow_gps;
+	int no_pi_lock;
 	const char *name;
 };
 
@@ -667,6 +675,7 @@ static struct rcu_torture_ops srcu_ops = {
 	.cb_barrier	= srcu_torture_barrier,
 	.stats		= srcu_torture_stats,
 	.irq_capable	= 1,
+	.no_pi_lock	= IS_ENABLED(CONFIG_TINY_SRCU),
 	.name		= "srcu"
 };
 
@@ -700,6 +709,7 @@ static struct rcu_torture_ops srcud_ops = {
 	.cb_barrier	= srcu_torture_barrier,
 	.stats		= srcu_torture_stats,
 	.irq_capable	= 1,
+	.no_pi_lock	= IS_ENABLED(CONFIG_TINY_SRCU),
 	.name		= "srcud"
 };
 
@@ -720,6 +730,7 @@ static struct rcu_torture_ops busted_srcud_ops = {
 	.cb_barrier	= srcu_torture_barrier,
 	.stats		= srcu_torture_stats,
 	.irq_capable	= 1,
+	.no_pi_lock	= IS_ENABLED(CONFIG_TINY_SRCU),
 	.extendables	= RCUTORTURE_MAX_EXTEND,
 	.name		= "busted_srcud"
 };
@@ -831,6 +842,7 @@ static struct rcu_torture_ops tasks_rude_ops = {
 	.call		= call_rcu_tasks_rude,
 	.cb_barrier	= rcu_barrier_tasks_rude,
 	.gp_kthread_dbg	= show_rcu_tasks_rude_gp_kthread,
+	.cbflood_max	= 50000,
 	.fqs		= NULL,
 	.stats		= NULL,
 	.irq_capable	= 1,
@@ -871,6 +883,7 @@ static struct rcu_torture_ops tasks_tracing_ops = {
 	.call		= call_rcu_tasks_trace,
 	.cb_barrier	= rcu_barrier_tasks_trace,
 	.gp_kthread_dbg	= show_rcu_tasks_trace_gp_kthread,
+	.cbflood_max	= 50000,
 	.fqs		= NULL,
 	.stats		= NULL,
 	.irq_capable	= 1,
@@ -1420,13 +1433,15 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 				  struct rt_read_seg *rtrsp)
 {
 	unsigned long flags;
-	int idxnew = -1;
-	int idxold = *readstate;
+	int idxnew1 = -1;
+	int idxnew2 = -1;
+	int idxold1 = *readstate;
+	int idxold2 = idxold1;
 	int statesnew = ~*readstate & newstate;
 	int statesold = *readstate & ~newstate;
 
-	WARN_ON_ONCE(idxold < 0);
-	WARN_ON_ONCE((idxold >> RCUTORTURE_RDR_SHIFT) > 1);
+	WARN_ON_ONCE(idxold2 < 0);
+	WARN_ON_ONCE((idxold2 >> RCUTORTURE_RDR_SHIFT_2) > 1);
 	rtrsp->rt_readstate = newstate;
 
 	/* First, put new protection in place to avoid critical-section gap. */
@@ -1440,8 +1455,10 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 		preempt_disable();
 	if (statesnew & RCUTORTURE_RDR_SCHED)
 		rcu_read_lock_sched();
-	if (statesnew & RCUTORTURE_RDR_RCU)
-		idxnew = cur_ops->readlock() << RCUTORTURE_RDR_SHIFT;
+	if (statesnew & RCUTORTURE_RDR_RCU_1)
+		idxnew1 = (cur_ops->readlock() & 0x1) << RCUTORTURE_RDR_SHIFT_1;
+	if (statesnew & RCUTORTURE_RDR_RCU_2)
+		idxnew2 = (cur_ops->readlock() & 0x1) << RCUTORTURE_RDR_SHIFT_2;
 
 	/*
 	 * Next, remove old protection, in decreasing order of strength
@@ -1460,12 +1477,20 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 		local_bh_enable();
 	if (statesold & RCUTORTURE_RDR_RBH)
 		rcu_read_unlock_bh();
-	if (statesold & RCUTORTURE_RDR_RCU) {
-		bool lockit = !statesnew && !(torture_random(trsp) & 0xffff);
+	if (statesold & RCUTORTURE_RDR_RCU_2) {
+		cur_ops->readunlock((idxold2 >> RCUTORTURE_RDR_SHIFT_2) & 0x1);
+		WARN_ON_ONCE(idxnew2 != -1);
+		idxold2 = 0;
+	}
+	if (statesold & RCUTORTURE_RDR_RCU_1) {
+		bool lockit;
 
+		lockit = !cur_ops->no_pi_lock && !statesnew && !(torture_random(trsp) & 0xffff);
 		if (lockit)
 			raw_spin_lock_irqsave(&current->pi_lock, flags);
-		cur_ops->readunlock(idxold >> RCUTORTURE_RDR_SHIFT);
+		cur_ops->readunlock((idxold1 >> RCUTORTURE_RDR_SHIFT_1) & 0x1);
+		WARN_ON_ONCE(idxnew1 != -1);
+		idxold1 = 0;
 		if (lockit)
 			raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 	}
@@ -1475,13 +1500,19 @@ static void rcutorture_one_extend(int *readstate, int newstate,
 		cur_ops->read_delay(trsp, rtrsp);
 
 	/* Update the reader state. */
-	if (idxnew == -1)
-		idxnew = idxold & ~RCUTORTURE_RDR_MASK;
-	WARN_ON_ONCE(idxnew < 0);
-	WARN_ON_ONCE((idxnew >> RCUTORTURE_RDR_SHIFT) > 1);
-	*readstate = idxnew | newstate;
-	WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT) < 0);
-	WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT) > 1);
+	if (idxnew1 == -1)
+		idxnew1 = idxold1 & RCUTORTURE_RDR_MASK_1;
+	WARN_ON_ONCE(idxnew1 < 0);
+	if (WARN_ON_ONCE((idxnew1 >> RCUTORTURE_RDR_SHIFT_1) > 1))
+		pr_info("Unexpected idxnew1 value of %#x\n", idxnew1);
+	if (idxnew2 == -1)
+		idxnew2 = idxold2 & RCUTORTURE_RDR_MASK_2;
+	WARN_ON_ONCE(idxnew2 < 0);
+	WARN_ON_ONCE((idxnew2 >> RCUTORTURE_RDR_SHIFT_2) > 1);
+	*readstate = idxnew1 | idxnew2 | newstate;
+	WARN_ON_ONCE(*readstate < 0);
+	if (WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT_2) > 1))
+		pr_info("Unexpected idxnew2 value of %#x\n", idxnew2);
 }
 
 /* Return the biggest extendables mask given current RCU and boot parameters. */
@@ -1491,7 +1522,7 @@ static int rcutorture_extend_mask_max(void)
 
 	WARN_ON_ONCE(extendables & ~RCUTORTURE_MAX_EXTEND);
 	mask = extendables & RCUTORTURE_MAX_EXTEND & cur_ops->extendables;
-	mask = mask | RCUTORTURE_RDR_RCU;
+	mask = mask | RCUTORTURE_RDR_RCU_1 | RCUTORTURE_RDR_RCU_2;
 	return mask;
 }
 
@@ -1506,13 +1537,21 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
 	unsigned long preempts_irq = preempts | RCUTORTURE_RDR_IRQ;
 	unsigned long bhs = RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH;
 
-	WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT);
+	WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT_1);
 	/* Mostly only one bit (need preemption!), sometimes lots of bits. */
 	if (!(randmask1 & 0x7))
 		mask = mask & randmask2;
 	else
 		mask = mask & (1 << (randmask2 % RCUTORTURE_RDR_NBITS));
 
+	// Can't have nested RCU reader without outer RCU reader.
+	if (!(mask & RCUTORTURE_RDR_RCU_1) && (mask & RCUTORTURE_RDR_RCU_2)) {
+		if (oldmask & RCUTORTURE_RDR_RCU_1)
+			mask &= ~RCUTORTURE_RDR_RCU_2;
+		else
+			mask |= RCUTORTURE_RDR_RCU_1;
+	}
+
 	/*
 	 * Can't enable bh w/irq disabled.
 	 */
@@ -1532,7 +1571,7 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
 			mask |= oldmask & bhs;
 	}
 
-	return mask ?: RCUTORTURE_RDR_RCU;
+	return mask ?: RCUTORTURE_RDR_RCU_1;
 }
 
 /*
@@ -1626,7 +1665,7 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp, long myid)
 			  rcu_torture_writer_state,
 			  cookie, cur_ops->get_gp_state());
 	rcutorture_one_extend(&readstate, 0, trsp, rtrsp);
-	WARN_ON_ONCE(readstate & RCUTORTURE_RDR_MASK);
+	WARN_ON_ONCE(readstate);
 	// This next splat is expected behavior if leakpointer, especially
 	// for CONFIG_RCU_STRICT_GRACE_PERIOD=y kernels.
 	WARN_ON_ONCE(leakpointer && READ_ONCE(p->rtort_pipe_count) > 1);
@@ -2052,6 +2091,8 @@ static int rcu_torture_stall(void *args)
 #else
 				schedule_timeout_uninterruptible(HZ);
 #endif
+			} else if (stall_no_softlockup) {
+				touch_softlockup_watchdog();
 			}
 		if (stall_cpu_irqsoff)
 			local_irq_enable();
@@ -2123,10 +2164,13 @@ struct rcu_fwd {
 	unsigned long rcu_fwd_startat;
 	struct rcu_launder_hist n_launders_hist[N_LAUNDERS_HIST];
 	unsigned long rcu_launder_gp_seq_start;
+	int rcu_fwd_id;
 };
 
 static DEFINE_MUTEX(rcu_fwd_mutex);
 static struct rcu_fwd *rcu_fwds;
+static unsigned long rcu_fwd_seq;
+static atomic_long_t rcu_fwd_max_cbs;
 static bool rcu_fwd_emergency_stop;
 
 static void rcu_torture_fwd_cb_hist(struct rcu_fwd *rfp)
@@ -2139,8 +2183,9 @@ static void rcu_torture_fwd_cb_hist(struct rcu_fwd *rfp)
 	for (i = ARRAY_SIZE(rfp->n_launders_hist) - 1; i > 0; i--)
 		if (rfp->n_launders_hist[i].n_launders > 0)
 			break;
-	pr_alert("%s: Callback-invocation histogram (duration %lu jiffies):",
-		 __func__, jiffies - rfp->rcu_fwd_startat);
+	mutex_lock(&rcu_fwd_mutex); // Serialize histograms.
+	pr_alert("%s: Callback-invocation histogram %d (duration %lu jiffies):",
+		 __func__, rfp->rcu_fwd_id, jiffies - rfp->rcu_fwd_startat);
 	gps_old = rfp->rcu_launder_gp_seq_start;
 	for (j = 0; j <= i; j++) {
 		gps = rfp->n_launders_hist[j].launder_gp_seq;
@@ -2151,6 +2196,7 @@ static void rcu_torture_fwd_cb_hist(struct rcu_fwd *rfp)
 		gps_old = gps;
 	}
 	pr_cont("\n");
+	mutex_unlock(&rcu_fwd_mutex);
 }
 
 /* Callback function for continuous-flood RCU callbacks. */
@@ -2276,7 +2322,8 @@ static void rcu_torture_fwd_prog_nr(struct rcu_fwd *rfp,
 		cver = READ_ONCE(rcu_torture_current_version) - cver;
 		gps = rcutorture_seq_diff(cur_ops->get_gp_seq(), gps);
 		WARN_ON(!cver && gps < 2);
-		pr_alert("%s: Duration %ld cver %ld gps %ld\n", __func__, dur, cver, gps);
+		pr_alert("%s: %d Duration %ld cver %ld gps %ld\n", __func__,
+			 rfp->rcu_fwd_id, dur, cver, gps);
 	}
 	if (selfpropcb) {
 		WRITE_ONCE(fcs.stop, 1);
@@ -2344,7 +2391,7 @@ static void rcu_torture_fwd_prog_cr(struct rcu_fwd *rfp)
 			rfp->rcu_fwd_cb_head = rfcpn;
 			n_launders++;
 			n_launders_sa++;
-		} else {
+		} else if (!cur_ops->cbflood_max || cur_ops->cbflood_max > n_max_cbs) {
 			rfcp = kmalloc(sizeof(*rfcp), GFP_KERNEL);
 			if (WARN_ON_ONCE(!rfcp)) {
 				schedule_timeout_interruptible(1);
@@ -2354,8 +2401,11 @@ static void rcu_torture_fwd_prog_cr(struct rcu_fwd *rfp)
 			n_launders_sa = 0;
 			rfcp->rfc_gps = 0;
 			rfcp->rfc_rfp = rfp;
+		} else {
+			rfcp = NULL;
 		}
-		cur_ops->call(&rfcp->rh, rcu_torture_fwd_cb_cr);
+		if (rfcp)
+			cur_ops->call(&rfcp->rh, rcu_torture_fwd_cb_cr);
 		rcu_torture_fwd_prog_cond_resched(n_launders + n_max_cbs);
 		if (tick_nohz_full_enabled()) {
 			local_irq_save(flags);
@@ -2379,6 +2429,7 @@ static void rcu_torture_fwd_prog_cr(struct rcu_fwd *rfp)
 			 n_launders + n_max_cbs - n_launders_cb_snap,
 			 n_launders, n_launders_sa,
 			 n_max_gps, n_max_cbs, cver, gps);
+		atomic_long_add(n_max_cbs, &rcu_fwd_max_cbs);
 		rcu_torture_fwd_cb_hist(rfp);
 	}
 	schedule_timeout_uninterruptible(HZ); /* Let CBs drain. */
@@ -2394,6 +2445,8 @@ static void rcu_torture_fwd_prog_cr(struct rcu_fwd *rfp)
 static int rcutorture_oom_notify(struct notifier_block *self,
 				 unsigned long notused, void *nfreed)
 {
+	int i;
+	long ncbs;
 	struct rcu_fwd *rfp;
 
 	mutex_lock(&rcu_fwd_mutex);
@@ -2404,18 +2457,26 @@ static int rcutorture_oom_notify(struct notifier_block *self,
 	}
 	WARN(1, "%s invoked upon OOM during forward-progress testing.\n",
 	     __func__);
-	rcu_torture_fwd_cb_hist(rfp);
-	rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rfp->rcu_fwd_startat)) / 2);
+	for (i = 0; i < fwd_progress; i++) {
+		rcu_torture_fwd_cb_hist(&rfp[i]);
+		rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rfp[i].rcu_fwd_startat)) / 2);
+	}
 	WRITE_ONCE(rcu_fwd_emergency_stop, true);
 	smp_mb(); /* Emergency stop before free and wait to avoid hangs. */
-	pr_info("%s: Freed %lu RCU callbacks.\n",
-		__func__, rcu_torture_fwd_prog_cbfree(rfp));
+	ncbs = 0;
+	for (i = 0; i < fwd_progress; i++)
+		ncbs += rcu_torture_fwd_prog_cbfree(&rfp[i]);
+	pr_info("%s: Freed %lu RCU callbacks.\n", __func__, ncbs);
 	rcu_barrier();
-	pr_info("%s: Freed %lu RCU callbacks.\n",
-		__func__, rcu_torture_fwd_prog_cbfree(rfp));
+	ncbs = 0;
+	for (i = 0; i < fwd_progress; i++)
+		ncbs += rcu_torture_fwd_prog_cbfree(&rfp[i]);
+	pr_info("%s: Freed %lu RCU callbacks.\n", __func__, ncbs);
 	rcu_barrier();
-	pr_info("%s: Freed %lu RCU callbacks.\n",
-		__func__, rcu_torture_fwd_prog_cbfree(rfp));
+	ncbs = 0;
+	for (i = 0; i < fwd_progress; i++)
+		ncbs += rcu_torture_fwd_prog_cbfree(&rfp[i]);
+	pr_info("%s: Freed %lu RCU callbacks.\n", __func__, ncbs);
 	smp_mb(); /* Frees before return to avoid redoing OOM. */
 	(*(unsigned long *)nfreed)++; /* Forward progress CBs freed! */
 	pr_info("%s returning after OOM processing.\n", __func__);
@@ -2430,7 +2491,10 @@ static struct notifier_block rcutorture_oom_nb = {
 /* Carry out grace-period forward-progress testing. */
 static int rcu_torture_fwd_prog(void *args)
 {
+	bool firsttime = true;
+	long max_cbs;
 	int oldnice = task_nice(current);
+	unsigned long oldseq = READ_ONCE(rcu_fwd_seq);
 	struct rcu_fwd *rfp = args;
 	int tested = 0;
 	int tested_tries = 0;
@@ -2440,21 +2504,38 @@ static int rcu_torture_fwd_prog(void *args)
 	if (!IS_ENABLED(CONFIG_SMP) || !IS_ENABLED(CONFIG_RCU_BOOST))
 		set_user_nice(current, MAX_NICE);
 	do {
-		schedule_timeout_interruptible(fwd_progress_holdoff * HZ);
-		WRITE_ONCE(rcu_fwd_emergency_stop, false);
-		if (!IS_ENABLED(CONFIG_TINY_RCU) ||
-		    rcu_inkernel_boot_has_ended())
-			rcu_torture_fwd_prog_nr(rfp, &tested, &tested_tries);
-		if (rcu_inkernel_boot_has_ended())
+		if (!rfp->rcu_fwd_id) {
+			schedule_timeout_interruptible(fwd_progress_holdoff * HZ);
+			WRITE_ONCE(rcu_fwd_emergency_stop, false);
+			if (!firsttime) {
+				max_cbs = atomic_long_xchg(&rcu_fwd_max_cbs, 0);
+				pr_alert("%s n_max_cbs: %ld\n", __func__, max_cbs);
+			}
+			firsttime = false;
+			WRITE_ONCE(rcu_fwd_seq, rcu_fwd_seq + 1);
+		} else {
+			while (READ_ONCE(rcu_fwd_seq) == oldseq)
+				schedule_timeout_interruptible(1);
+			oldseq = READ_ONCE(rcu_fwd_seq);
+		}
+		pr_alert("%s: Starting forward-progress test %d\n", __func__, rfp->rcu_fwd_id);
+		if (rcu_inkernel_boot_has_ended() && torture_num_online_cpus() > rfp->rcu_fwd_id)
 			rcu_torture_fwd_prog_cr(rfp);
+		if ((cur_ops->stall_dur && cur_ops->stall_dur() > 0) &&
+		    (!IS_ENABLED(CONFIG_TINY_RCU) ||
+		     (rcu_inkernel_boot_has_ended() &&
+		      torture_num_online_cpus() > rfp->rcu_fwd_id)))
+			rcu_torture_fwd_prog_nr(rfp, &tested, &tested_tries);
 
 		/* Avoid slow periods, better to test when busy. */
 		if (stutter_wait("rcu_torture_fwd_prog"))
 			sched_set_normal(current, oldnice);
 	} while (!torture_must_stop());
 	/* Short runs might not contain a valid forward-progress attempt. */
-	WARN_ON(!tested && tested_tries >= 5);
-	pr_alert("%s: tested %d tested_tries %d\n", __func__, tested, tested_tries);
+	if (!rfp->rcu_fwd_id) {
+		WARN_ON(!tested && tested_tries >= 5);
+		pr_alert("%s: tested %d tested_tries %d\n", __func__, tested, tested_tries);
+	}
 	torture_kthread_stopping("rcu_torture_fwd_prog");
 	return 0;
 }
@@ -2462,17 +2543,28 @@ static int rcu_torture_fwd_prog(void *args)
 /* If forward-progress checking is requested and feasible, spawn the thread. */
 static int __init rcu_torture_fwd_prog_init(void)
 {
+	int i;
+	int ret = 0;
 	struct rcu_fwd *rfp;
 
 	if (!fwd_progress)
 		return 0; /* Not requested, so don't do it. */
+	if (fwd_progress >= nr_cpu_ids) {
+		VERBOSE_TOROUT_STRING("rcu_torture_fwd_prog_init: Limiting fwd_progress to # CPUs.\n");
+		fwd_progress = nr_cpu_ids;
+	} else if (fwd_progress < 0) {
+		fwd_progress = nr_cpu_ids;
+	}
 	if ((!cur_ops->sync && !cur_ops->call) ||
-	    !cur_ops->stall_dur || cur_ops->stall_dur() <= 0 || cur_ops == &rcu_busted_ops) {
+	    (!cur_ops->cbflood_max && (!cur_ops->stall_dur || cur_ops->stall_dur() <= 0)) ||
+	    cur_ops == &rcu_busted_ops) {
 		VERBOSE_TOROUT_STRING("rcu_torture_fwd_prog_init: Disabled, unsupported by RCU flavor under test");
+		fwd_progress = 0;
 		return 0;
 	}
 	if (stall_cpu > 0) {
 		VERBOSE_TOROUT_STRING("rcu_torture_fwd_prog_init: Disabled, conflicts with CPU-stall testing");
+		fwd_progress = 0;
 		if (IS_MODULE(CONFIG_RCU_TORTURE_TEST))
 			return -EINVAL; /* In module, can fail back to user. */
 		WARN_ON(1); /* Make sure rcutorture notices conflict. */
@@ -2482,29 +2574,51 @@ static int __init rcu_torture_fwd_prog_init(void)
 		fwd_progress_holdoff = 1;
 	if (fwd_progress_div <= 0)
 		fwd_progress_div = 4;
-	rfp = kzalloc(sizeof(*rfp), GFP_KERNEL);
-	if (!rfp)
+	rfp = kcalloc(fwd_progress, sizeof(*rfp), GFP_KERNEL);
+	fwd_prog_tasks = kcalloc(fwd_progress, sizeof(*fwd_prog_tasks), GFP_KERNEL);
+	if (!rfp || !fwd_prog_tasks) {
+		kfree(rfp);
+		kfree(fwd_prog_tasks);
+		fwd_prog_tasks = NULL;
+		fwd_progress = 0;
 		return -ENOMEM;
-	spin_lock_init(&rfp->rcu_fwd_lock);
-	rfp->rcu_fwd_cb_tail = &rfp->rcu_fwd_cb_head;
+	}
+	for (i = 0; i < fwd_progress; i++) {
+		spin_lock_init(&rfp[i].rcu_fwd_lock);
+		rfp[i].rcu_fwd_cb_tail = &rfp[i].rcu_fwd_cb_head;
+		rfp[i].rcu_fwd_id = i;
+	}
 	mutex_lock(&rcu_fwd_mutex);
 	rcu_fwds = rfp;
 	mutex_unlock(&rcu_fwd_mutex);
 	register_oom_notifier(&rcutorture_oom_nb);
-	return torture_create_kthread(rcu_torture_fwd_prog, rfp, fwd_prog_task);
+	for (i = 0; i < fwd_progress; i++) {
+		ret = torture_create_kthread(rcu_torture_fwd_prog, &rcu_fwds[i], fwd_prog_tasks[i]);
+		if (ret) {
+			fwd_progress = i;
+			return ret;
+		}
+	}
+	return 0;
 }
 
 static void rcu_torture_fwd_prog_cleanup(void)
 {
+	int i;
 	struct rcu_fwd *rfp;
 
-	torture_stop_kthread(rcu_torture_fwd_prog, fwd_prog_task);
-	rfp = rcu_fwds;
+	if (!rcu_fwds || !fwd_prog_tasks)
+		return;
+	for (i = 0; i < fwd_progress; i++)
+		torture_stop_kthread(rcu_torture_fwd_prog, fwd_prog_tasks[i]);
+	unregister_oom_notifier(&rcutorture_oom_nb);
 	mutex_lock(&rcu_fwd_mutex);
+	rfp = rcu_fwds;
 	rcu_fwds = NULL;
 	mutex_unlock(&rcu_fwd_mutex);
-	unregister_oom_notifier(&rcutorture_oom_nb);
 	kfree(rfp);
+	kfree(fwd_prog_tasks);
+	fwd_prog_tasks = NULL;
 }
 
 /* Callback function for RCU barrier testing. */
@@ -2741,7 +2855,7 @@ static int rcu_torture_read_exit(void *unused)
 				     &trs, "%s",
 				     "rcu_torture_read_exit_child");
 		if (IS_ERR(tsp)) {
-			VERBOSE_TOROUT_ERRSTRING("out of memory");
+			TOROUT_ERRSTRING("out of memory");
 			errexit = true;
 			tsp = NULL;
 			break;
@@ -3068,7 +3182,7 @@ rcu_torture_init(void)
 					   sizeof(fakewriter_tasks[0]),
 					   GFP_KERNEL);
 		if (fakewriter_tasks == NULL) {
-			VERBOSE_TOROUT_ERRSTRING("out of memory");
+			TOROUT_ERRSTRING("out of memory");
 			firsterr = -ENOMEM;
 			goto unwind;
 		}
@@ -3084,7 +3198,7 @@ rcu_torture_init(void)
 	rcu_torture_reader_mbchk = kcalloc(nrealreaders, sizeof(*rcu_torture_reader_mbchk),
 					   GFP_KERNEL);
 	if (!reader_tasks || !rcu_torture_reader_mbchk) {
-		VERBOSE_TOROUT_ERRSTRING("out of memory");
+		TOROUT_ERRSTRING("out of memory");
 		firsterr = -ENOMEM;
 		goto unwind;
 	}
@@ -3103,7 +3217,7 @@ rcu_torture_init(void)
 	if (nrealnocbers > 0) {
 		nocb_tasks = kcalloc(nrealnocbers, sizeof(nocb_tasks[0]), GFP_KERNEL);
 		if (nocb_tasks == NULL) {
-			VERBOSE_TOROUT_ERRSTRING("out of memory");
+			TOROUT_ERRSTRING("out of memory");
 			firsterr = -ENOMEM;
 			goto unwind;
 		}
diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c
index 1631ef8a138d..5489ff7f478e 100644
--- a/kernel/rcu/refscale.c
+++ b/kernel/rcu/refscale.c
@@ -44,7 +44,10 @@
 	pr_alert("%s" SCALE_FLAG s, scale_type, ## x)
 
 #define VERBOSE_SCALEOUT(s, x...) \
-	do { if (verbose) pr_alert("%s" SCALE_FLAG s, scale_type, ## x); } while (0)
+	do { \
+		if (verbose) \
+			pr_alert("%s" SCALE_FLAG s "\n", scale_type, ## x); \
+	} while (0)
 
 static atomic_t verbose_batch_ctr;
 
@@ -54,12 +57,11 @@ do {											\
 	    (verbose_batched <= 0 ||							\
 	     !(atomic_inc_return(&verbose_batch_ctr) % verbose_batched))) {		\
 		schedule_timeout_uninterruptible(1);					\
-		pr_alert("%s" SCALE_FLAG s, scale_type, ## x);				\
+		pr_alert("%s" SCALE_FLAG s "\n", scale_type, ## x);			\
 	}										\
 } while (0)
 
-#define VERBOSE_SCALEOUT_ERRSTRING(s, x...) \
-	do { if (verbose) pr_alert("%s" SCALE_FLAG "!!! " s, scale_type, ## x); } while (0)
+#define SCALEOUT_ERRSTRING(s, x...) pr_alert("%s" SCALE_FLAG "!!! " s "\n", scale_type, ## x)
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Joel Fernandes (Google) <joel@joelfernandes.org>");
@@ -604,7 +606,7 @@ static u64 process_durations(int n)
 	char *buf;
 	u64 sum = 0;
 
-	buf = kmalloc(128 + nreaders * 32, GFP_KERNEL);
+	buf = kmalloc(800 + 64, GFP_KERNEL);
 	if (!buf)
 		return 0;
 	buf[0] = 0;
@@ -617,13 +619,15 @@ static u64 process_durations(int n)
 
 		if (i % 5 == 0)
 			strcat(buf, "\n");
+		if (strlen(buf) >= 800) {
+			pr_alert("%s", buf);
+			buf[0] = 0;
+		}
 		strcat(buf, buf1);
 
 		sum += rt->last_duration_ns;
 	}
-	strcat(buf, "\n");
-
-	SCALEOUT("%s\n", buf);
+	pr_alert("%s\n", buf);
 
 	kfree(buf);
 	return sum;
@@ -637,7 +641,6 @@ static u64 process_durations(int n)
 // point all the timestamps are printed.
 static int main_func(void *arg)
 {
-	bool errexit = false;
 	int exp, r;
 	char buf1[64];
 	char *buf;
@@ -648,10 +651,10 @@ static int main_func(void *arg)
 
 	VERBOSE_SCALEOUT("main_func task started");
 	result_avg = kzalloc(nruns * sizeof(*result_avg), GFP_KERNEL);
-	buf = kzalloc(64 + nruns * 32, GFP_KERNEL);
+	buf = kzalloc(800 + 64, GFP_KERNEL);
 	if (!result_avg || !buf) {
-		VERBOSE_SCALEOUT_ERRSTRING("out of memory");
-		errexit = true;
+		SCALEOUT_ERRSTRING("out of memory");
+		goto oom_exit;
 	}
 	if (holdoff)
 		schedule_timeout_interruptible(holdoff * HZ);
@@ -663,8 +666,6 @@ static int main_func(void *arg)
 
 	// Start exp readers up per experiment
 	for (exp = 0; exp < nruns && !torture_must_stop(); exp++) {
-		if (errexit)
-			break;
 		if (torture_must_stop())
 			goto end;
 
@@ -698,26 +699,23 @@ static int main_func(void *arg)
 	// Print the average of all experiments
 	SCALEOUT("END OF TEST. Calculating average duration per loop (nanoseconds)...\n");
 
-	if (!errexit) {
-		buf[0] = 0;
-		strcat(buf, "\n");
-		strcat(buf, "Runs\tTime(ns)\n");
-	}
-
+	pr_alert("Runs\tTime(ns)\n");
 	for (exp = 0; exp < nruns; exp++) {
 		u64 avg;
 		u32 rem;
 
-		if (errexit)
-			break;
 		avg = div_u64_rem(result_avg[exp], 1000, &rem);
 		sprintf(buf1, "%d\t%llu.%03u\n", exp + 1, avg, rem);
 		strcat(buf, buf1);
+		if (strlen(buf) >= 800) {
+			pr_alert("%s", buf);
+			buf[0] = 0;
+		}
 	}
 
-	if (!errexit)
-		SCALEOUT("%s", buf);
+	pr_alert("%s", buf);
 
+oom_exit:
 	// This will shutdown everything including us.
 	if (shutdown) {
 		shutdown_start = 1;
@@ -841,12 +839,12 @@ ref_scale_init(void)
 	reader_tasks = kcalloc(nreaders, sizeof(reader_tasks[0]),
 			       GFP_KERNEL);
 	if (!reader_tasks) {
-		VERBOSE_SCALEOUT_ERRSTRING("out of memory");
+		SCALEOUT_ERRSTRING("out of memory");
 		firsterr = -ENOMEM;
 		goto unwind;
 	}
 
-	VERBOSE_SCALEOUT("Starting %d reader threads\n", nreaders);
+	VERBOSE_SCALEOUT("Starting %d reader threads", nreaders);
 
 	for (i = 0; i < nreaders; i++) {
 		firsterr = torture_create_kthread(ref_scale_reader, (void *)i,
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index a0ba2ed49bc6..92c002d65482 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -99,7 +99,7 @@ void __srcu_read_unlock(struct srcu_struct *ssp, int idx)
 	int newval = READ_ONCE(ssp->srcu_lock_nesting[idx]) - 1;
 
 	WRITE_ONCE(ssp->srcu_lock_nesting[idx], newval);
-	if (!newval && READ_ONCE(ssp->srcu_gp_waiting))
+	if (!newval && READ_ONCE(ssp->srcu_gp_waiting) && in_task())
 		swake_up_one(&ssp->srcu_wq);
 }
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 7da3c81c3f59..84f1d91604cc 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -6,6 +6,7 @@
  */
 
 #ifdef CONFIG_TASKS_RCU_GENERIC
+#include "rcu_segcblist.h"
 
 ////////////////////////////////////////////////////////////////////////
 //
@@ -20,11 +21,33 @@ typedef void (*holdouts_func_t)(struct list_head *hop, bool ndrpt, bool *frptp);
 typedef void (*postgp_func_t)(struct rcu_tasks *rtp);
 
 /**
+ * struct rcu_tasks_percpu - Per-CPU component of definition for a Tasks-RCU-like mechanism.
+ * @cblist: Callback list.
+ * @lock: Lock protecting per-CPU callback list.
+ * @rtp_jiffies: Jiffies counter value for statistics.
+ * @rtp_n_lock_retries: Rough lock-contention statistic.
+ * @rtp_work: Work queue for invoking callbacks.
+ * @rtp_irq_work: IRQ work queue for deferred wakeups.
+ * @barrier_q_head: RCU callback for barrier operation.
+ * @cpu: CPU number corresponding to this entry.
+ * @rtpp: Pointer to the rcu_tasks structure.
+ */
+struct rcu_tasks_percpu {
+	struct rcu_segcblist cblist;
+	raw_spinlock_t __private lock;
+	unsigned long rtp_jiffies;
+	unsigned long rtp_n_lock_retries;
+	struct work_struct rtp_work;
+	struct irq_work rtp_irq_work;
+	struct rcu_head barrier_q_head;
+	int cpu;
+	struct rcu_tasks *rtpp;
+};
+
+/**
  * struct rcu_tasks - Definition for a Tasks-RCU-like mechanism.
- * @cbs_head: Head of callback list.
- * @cbs_tail: Tail pointer for callback list.
  * @cbs_wq: Wait queue allowing new callback to get kthread's attention.
- * @cbs_lock: Lock protecting callback list.
+ * @cbs_gbl_lock: Lock protecting callback list.
  * @kthread_ptr: This flavor's grace-period/callback-invocation kthread.
  * @gp_func: This flavor's grace-period-wait function.
  * @gp_state: Grace period's most recent state transition (debugging).
@@ -32,7 +55,7 @@ typedef void (*postgp_func_t)(struct rcu_tasks *rtp);
  * @init_fract: Initial backoff sleep interval.
  * @gp_jiffies: Time of last @gp_state transition.
  * @gp_start: Most recent grace-period start in jiffies.
- * @n_gps: Number of grace periods completed since boot.
+ * @tasks_gp_seq: Number of grace periods completed since boot.
  * @n_ipis: Number of IPIs sent to encourage grace periods to end.
  * @n_ipis_fails: Number of IPI-send failures.
  * @pregp_func: This flavor's pre-grace-period function (optional).
@@ -41,20 +64,27 @@ typedef void (*postgp_func_t)(struct rcu_tasks *rtp);
  * @holdouts_func: This flavor's holdout-list scan function (optional).
  * @postgp_func: This flavor's post-grace-period function (optional).
  * @call_func: This flavor's call_rcu()-equivalent function.
+ * @rtpcpu: This flavor's rcu_tasks_percpu structure.
+ * @percpu_enqueue_shift: Shift down CPU ID this much when enqueuing callbacks.
+ * @percpu_enqueue_lim: Number of per-CPU callback queues in use for enqueuing.
+ * @percpu_dequeue_lim: Number of per-CPU callback queues in use for dequeuing.
+ * @percpu_dequeue_gpseq: RCU grace-period number to propagate enqueue limit to dequeuers.
+ * @barrier_q_mutex: Serialize barrier operations.
+ * @barrier_q_count: Number of queues being waited on.
+ * @barrier_q_completion: Barrier wait/wakeup mechanism.
+ * @barrier_q_seq: Sequence number for barrier operations.
  * @name: This flavor's textual name.
  * @kname: This flavor's kthread name.
  */
 struct rcu_tasks {
-	struct rcu_head *cbs_head;
-	struct rcu_head **cbs_tail;
 	struct wait_queue_head cbs_wq;
-	raw_spinlock_t cbs_lock;
+	raw_spinlock_t cbs_gbl_lock;
 	int gp_state;
 	int gp_sleep;
 	int init_fract;
 	unsigned long gp_jiffies;
 	unsigned long gp_start;
-	unsigned long n_gps;
+	unsigned long tasks_gp_seq;
 	unsigned long n_ipis;
 	unsigned long n_ipis_fails;
 	struct task_struct *kthread_ptr;
@@ -65,20 +95,40 @@ struct rcu_tasks {
 	holdouts_func_t holdouts_func;
 	postgp_func_t postgp_func;
 	call_rcu_func_t call_func;
+	struct rcu_tasks_percpu __percpu *rtpcpu;
+	int percpu_enqueue_shift;
+	int percpu_enqueue_lim;
+	int percpu_dequeue_lim;
+	unsigned long percpu_dequeue_gpseq;
+	struct mutex barrier_q_mutex;
+	atomic_t barrier_q_count;
+	struct completion barrier_q_completion;
+	unsigned long barrier_q_seq;
 	char *name;
 	char *kname;
 };
 
-#define DEFINE_RCU_TASKS(rt_name, gp, call, n)				\
-static struct rcu_tasks rt_name =					\
-{									\
-	.cbs_tail = &rt_name.cbs_head,					\
-	.cbs_wq = __WAIT_QUEUE_HEAD_INITIALIZER(rt_name.cbs_wq),	\
-	.cbs_lock = __RAW_SPIN_LOCK_UNLOCKED(rt_name.cbs_lock),		\
-	.gp_func = gp,							\
-	.call_func = call,						\
-	.name = n,							\
-	.kname = #rt_name,						\
+static void call_rcu_tasks_iw_wakeup(struct irq_work *iwp);
+
+#define DEFINE_RCU_TASKS(rt_name, gp, call, n)						\
+static DEFINE_PER_CPU(struct rcu_tasks_percpu, rt_name ## __percpu) = {			\
+	.lock = __RAW_SPIN_LOCK_UNLOCKED(rt_name ## __percpu.cbs_pcpu_lock),		\
+	.rtp_irq_work = IRQ_WORK_INIT(call_rcu_tasks_iw_wakeup),			\
+};											\
+static struct rcu_tasks rt_name =							\
+{											\
+	.cbs_wq = __WAIT_QUEUE_HEAD_INITIALIZER(rt_name.cbs_wq),			\
+	.cbs_gbl_lock = __RAW_SPIN_LOCK_UNLOCKED(rt_name.cbs_gbl_lock),			\
+	.gp_func = gp,									\
+	.call_func = call,								\
+	.rtpcpu = &rt_name ## __percpu,							\
+	.name = n,									\
+	.percpu_enqueue_shift = ilog2(CONFIG_NR_CPUS),					\
+	.percpu_enqueue_lim = 1,							\
+	.percpu_dequeue_lim = 1,							\
+	.barrier_q_mutex = __MUTEX_INITIALIZER(rt_name.barrier_q_mutex),		\
+	.barrier_q_seq = (0UL - 50UL) << RCU_SEQ_CTR_SHIFT,				\
+	.kname = #rt_name,								\
 }
 
 /* Track exiting tasks in order to allow them to be waited for. */
@@ -94,6 +144,15 @@ module_param(rcu_task_ipi_delay, int, 0644);
 static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT;
 module_param(rcu_task_stall_timeout, int, 0644);
 
+static int rcu_task_enqueue_lim __read_mostly = -1;
+module_param(rcu_task_enqueue_lim, int, 0444);
+
+static bool rcu_task_cb_adjust;
+static int rcu_task_contend_lim __read_mostly = 100;
+module_param(rcu_task_contend_lim, int, 0444);
+static int rcu_task_collapse_lim __read_mostly = 10;
+module_param(rcu_task_collapse_lim, int, 0444);
+
 /* RCU tasks grace-period state for debugging. */
 #define RTGS_INIT		 0
 #define RTGS_WAIT_WAIT_CBS	 1
@@ -128,6 +187,8 @@ static const char * const rcu_tasks_gp_state_names[] = {
 //
 // Generic code.
 
+static void rcu_tasks_invoke_cbs_wq(struct work_struct *wp);
+
 /* Record grace-period phase and time. */
 static void set_tasks_gp_state(struct rcu_tasks *rtp, int newstate)
 {
@@ -148,23 +209,106 @@ static const char *tasks_gp_state_getname(struct rcu_tasks *rtp)
 }
 #endif /* #ifndef CONFIG_TINY_RCU */
 
+// Initialize per-CPU callback lists for the specified flavor of
+// Tasks RCU.
+static void cblist_init_generic(struct rcu_tasks *rtp)
+{
+	int cpu;
+	unsigned long flags;
+	int lim;
+
+	raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags);
+	if (rcu_task_enqueue_lim < 0) {
+		rcu_task_enqueue_lim = 1;
+		rcu_task_cb_adjust = true;
+		pr_info("%s: Setting adjustable number of callback queues.\n", __func__);
+	} else if (rcu_task_enqueue_lim == 0) {
+		rcu_task_enqueue_lim = 1;
+	}
+	lim = rcu_task_enqueue_lim;
+
+	if (lim > nr_cpu_ids)
+		lim = nr_cpu_ids;
+	WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids / lim));
+	WRITE_ONCE(rtp->percpu_dequeue_lim, lim);
+	smp_store_release(&rtp->percpu_enqueue_lim, lim);
+	for_each_possible_cpu(cpu) {
+		struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
+
+		WARN_ON_ONCE(!rtpcp);
+		if (cpu)
+			raw_spin_lock_init(&ACCESS_PRIVATE(rtpcp, lock));
+		raw_spin_lock_rcu_node(rtpcp); // irqs already disabled.
+		if (rcu_segcblist_empty(&rtpcp->cblist))
+			rcu_segcblist_init(&rtpcp->cblist);
+		INIT_WORK(&rtpcp->rtp_work, rcu_tasks_invoke_cbs_wq);
+		rtpcp->cpu = cpu;
+		rtpcp->rtpp = rtp;
+		raw_spin_unlock_rcu_node(rtpcp); // irqs remain disabled.
+	}
+	raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags);
+	pr_info("%s: Setting shift to %d and lim to %d.\n", __func__, data_race(rtp->percpu_enqueue_shift), data_race(rtp->percpu_enqueue_lim));
+}
+
+// IRQ-work handler that does deferred wakeup for call_rcu_tasks_generic().
+static void call_rcu_tasks_iw_wakeup(struct irq_work *iwp)
+{
+	struct rcu_tasks *rtp;
+	struct rcu_tasks_percpu *rtpcp = container_of(iwp, struct rcu_tasks_percpu, rtp_irq_work);
+
+	rtp = rtpcp->rtpp;
+	wake_up(&rtp->cbs_wq);
+}
+
 // Enqueue a callback for the specified flavor of Tasks RCU.
 static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func,
 				   struct rcu_tasks *rtp)
 {
 	unsigned long flags;
+	unsigned long j;
+	bool needadjust = false;
 	bool needwake;
+	struct rcu_tasks_percpu *rtpcp;
 
 	rhp->next = NULL;
 	rhp->func = func;
-	raw_spin_lock_irqsave(&rtp->cbs_lock, flags);
-	needwake = !rtp->cbs_head;
-	WRITE_ONCE(*rtp->cbs_tail, rhp);
-	rtp->cbs_tail = &rhp->next;
-	raw_spin_unlock_irqrestore(&rtp->cbs_lock, flags);
+	local_irq_save(flags);
+	rcu_read_lock();
+	rtpcp = per_cpu_ptr(rtp->rtpcpu,
+			    smp_processor_id() >> READ_ONCE(rtp->percpu_enqueue_shift));
+	if (!raw_spin_trylock_rcu_node(rtpcp)) { // irqs already disabled.
+		raw_spin_lock_rcu_node(rtpcp); // irqs already disabled.
+		j = jiffies;
+		if (rtpcp->rtp_jiffies != j) {
+			rtpcp->rtp_jiffies = j;
+			rtpcp->rtp_n_lock_retries = 0;
+		}
+		if (rcu_task_cb_adjust && ++rtpcp->rtp_n_lock_retries > rcu_task_contend_lim &&
+		    READ_ONCE(rtp->percpu_enqueue_lim) != nr_cpu_ids)
+			needadjust = true;  // Defer adjustment to avoid deadlock.
+	}
+	if (!rcu_segcblist_is_enabled(&rtpcp->cblist)) {
+		raw_spin_unlock_rcu_node(rtpcp); // irqs remain disabled.
+		cblist_init_generic(rtp);
+		raw_spin_lock_rcu_node(rtpcp); // irqs already disabled.
+	}
+	needwake = rcu_segcblist_empty(&rtpcp->cblist);
+	rcu_segcblist_enqueue(&rtpcp->cblist, rhp);
+	raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
+	if (unlikely(needadjust)) {
+		raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags);
+		if (rtp->percpu_enqueue_lim != nr_cpu_ids) {
+			WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids));
+			WRITE_ONCE(rtp->percpu_dequeue_lim, nr_cpu_ids);
+			smp_store_release(&rtp->percpu_enqueue_lim, nr_cpu_ids);
+			pr_info("Switching %s to per-CPU callback queuing.\n", rtp->name);
+		}
+		raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags);
+	}
+	rcu_read_unlock();
 	/* We can't create the thread unless interrupts are enabled. */
 	if (needwake && READ_ONCE(rtp->kthread_ptr))
-		wake_up(&rtp->cbs_wq);
+		irq_work_queue(&rtpcp->rtp_irq_work);
 }
 
 // Wait for a grace period for the specified flavor of Tasks RCU.
@@ -178,12 +322,173 @@ static void synchronize_rcu_tasks_generic(struct rcu_tasks *rtp)
 	wait_rcu_gp(rtp->call_func);
 }
 
+// RCU callback function for rcu_barrier_tasks_generic().
+static void rcu_barrier_tasks_generic_cb(struct rcu_head *rhp)
+{
+	struct rcu_tasks *rtp;
+	struct rcu_tasks_percpu *rtpcp;
+
+	rtpcp = container_of(rhp, struct rcu_tasks_percpu, barrier_q_head);
+	rtp = rtpcp->rtpp;
+	if (atomic_dec_and_test(&rtp->barrier_q_count))
+		complete(&rtp->barrier_q_completion);
+}
+
+// Wait for all in-flight callbacks for the specified RCU Tasks flavor.
+// Operates in a manner similar to rcu_barrier().
+static void rcu_barrier_tasks_generic(struct rcu_tasks *rtp)
+{
+	int cpu;
+	unsigned long flags;
+	struct rcu_tasks_percpu *rtpcp;
+	unsigned long s = rcu_seq_snap(&rtp->barrier_q_seq);
+
+	mutex_lock(&rtp->barrier_q_mutex);
+	if (rcu_seq_done(&rtp->barrier_q_seq, s)) {
+		smp_mb();
+		mutex_unlock(&rtp->barrier_q_mutex);
+		return;
+	}
+	rcu_seq_start(&rtp->barrier_q_seq);
+	init_completion(&rtp->barrier_q_completion);
+	atomic_set(&rtp->barrier_q_count, 2);
+	for_each_possible_cpu(cpu) {
+		if (cpu >= smp_load_acquire(&rtp->percpu_dequeue_lim))
+			break;
+		rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
+		rtpcp->barrier_q_head.func = rcu_barrier_tasks_generic_cb;
+		raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
+		if (rcu_segcblist_entrain(&rtpcp->cblist, &rtpcp->barrier_q_head))
+			atomic_inc(&rtp->barrier_q_count);
+		raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
+	}
+	if (atomic_sub_and_test(2, &rtp->barrier_q_count))
+		complete(&rtp->barrier_q_completion);
+	wait_for_completion(&rtp->barrier_q_completion);
+	rcu_seq_end(&rtp->barrier_q_seq);
+	mutex_unlock(&rtp->barrier_q_mutex);
+}
+
+// Advance callbacks and indicate whether either a grace period or
+// callback invocation is needed.
+static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp)
+{
+	int cpu;
+	unsigned long flags;
+	long n;
+	long ncbs = 0;
+	long ncbsnz = 0;
+	int needgpcb = 0;
+
+	for (cpu = 0; cpu < smp_load_acquire(&rtp->percpu_dequeue_lim); cpu++) {
+		struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
+
+		/* Advance and accelerate any new callbacks. */
+		if (!rcu_segcblist_n_cbs(&rtpcp->cblist))
+			continue;
+		raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
+		// Should we shrink down to a single callback queue?
+		n = rcu_segcblist_n_cbs(&rtpcp->cblist);
+		if (n) {
+			ncbs += n;
+			if (cpu > 0)
+				ncbsnz += n;
+		}
+		rcu_segcblist_advance(&rtpcp->cblist, rcu_seq_current(&rtp->tasks_gp_seq));
+		(void)rcu_segcblist_accelerate(&rtpcp->cblist, rcu_seq_snap(&rtp->tasks_gp_seq));
+		if (rcu_segcblist_pend_cbs(&rtpcp->cblist))
+			needgpcb |= 0x3;
+		if (!rcu_segcblist_empty(&rtpcp->cblist))
+			needgpcb |= 0x1;
+		raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
+	}
+
+	// Shrink down to a single callback queue if appropriate.
+	// This is done in two stages: (1) If there are no more than
+	// rcu_task_collapse_lim callbacks on CPU 0 and none on any other
+	// CPU, limit enqueueing to CPU 0.  (2) After an RCU grace period,
+	// if there has not been an increase in callbacks, limit dequeuing
+	// to CPU 0.  Note the matching RCU read-side critical section in
+	// call_rcu_tasks_generic().
+	if (rcu_task_cb_adjust && ncbs <= rcu_task_collapse_lim) {
+		raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags);
+		if (rtp->percpu_enqueue_lim > 1) {
+			WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids));
+			smp_store_release(&rtp->percpu_enqueue_lim, 1);
+			rtp->percpu_dequeue_gpseq = get_state_synchronize_rcu();
+			pr_info("Starting switch %s to CPU-0 callback queuing.\n", rtp->name);
+		}
+		raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags);
+	}
+	if (rcu_task_cb_adjust && !ncbsnz &&
+	    poll_state_synchronize_rcu(rtp->percpu_dequeue_gpseq)) {
+		raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags);
+		if (rtp->percpu_enqueue_lim < rtp->percpu_dequeue_lim) {
+			WRITE_ONCE(rtp->percpu_dequeue_lim, 1);
+			pr_info("Completing switch %s to CPU-0 callback queuing.\n", rtp->name);
+		}
+		raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags);
+	}
+
+	return needgpcb;
+}
+
+// Advance callbacks and invoke any that are ready.
+static void rcu_tasks_invoke_cbs(struct rcu_tasks *rtp, struct rcu_tasks_percpu *rtpcp)
+{
+	int cpu;
+	int cpunext;
+	unsigned long flags;
+	int len;
+	struct rcu_head *rhp;
+	struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl);
+	struct rcu_tasks_percpu *rtpcp_next;
+
+	cpu = rtpcp->cpu;
+	cpunext = cpu * 2 + 1;
+	if (cpunext < smp_load_acquire(&rtp->percpu_dequeue_lim)) {
+		rtpcp_next = per_cpu_ptr(rtp->rtpcpu, cpunext);
+		queue_work_on(cpunext, system_wq, &rtpcp_next->rtp_work);
+		cpunext++;
+		if (cpunext < smp_load_acquire(&rtp->percpu_dequeue_lim)) {
+			rtpcp_next = per_cpu_ptr(rtp->rtpcpu, cpunext);
+			queue_work_on(cpunext, system_wq, &rtpcp_next->rtp_work);
+		}
+	}
+
+	if (rcu_segcblist_empty(&rtpcp->cblist))
+		return;
+	raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
+	rcu_segcblist_advance(&rtpcp->cblist, rcu_seq_current(&rtp->tasks_gp_seq));
+	rcu_segcblist_extract_done_cbs(&rtpcp->cblist, &rcl);
+	raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
+	len = rcl.len;
+	for (rhp = rcu_cblist_dequeue(&rcl); rhp; rhp = rcu_cblist_dequeue(&rcl)) {
+		local_bh_disable();
+		rhp->func(rhp);
+		local_bh_enable();
+		cond_resched();
+	}
+	raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
+	rcu_segcblist_add_len(&rtpcp->cblist, -len);
+	(void)rcu_segcblist_accelerate(&rtpcp->cblist, rcu_seq_snap(&rtp->tasks_gp_seq));
+	raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
+}
+
+// Workqueue flood to advance callbacks and invoke any that are ready.
+static void rcu_tasks_invoke_cbs_wq(struct work_struct *wp)
+{
+	struct rcu_tasks *rtp;
+	struct rcu_tasks_percpu *rtpcp = container_of(wp, struct rcu_tasks_percpu, rtp_work);
+
+	rtp = rtpcp->rtpp;
+	rcu_tasks_invoke_cbs(rtp, rtpcp);
+}
+
 /* RCU-tasks kthread that detects grace periods and invokes callbacks. */
 static int __noreturn rcu_tasks_kthread(void *arg)
 {
-	unsigned long flags;
-	struct rcu_head *list;
-	struct rcu_head *next;
+	int needgpcb;
 	struct rcu_tasks *rtp = arg;
 
 	/* Run on housekeeping CPUs by default.  Sysadm can move if desired. */
@@ -199,42 +504,22 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 	for (;;) {
 		set_tasks_gp_state(rtp, RTGS_WAIT_CBS);
 
-		/* Pick up any new callbacks. */
-		raw_spin_lock_irqsave(&rtp->cbs_lock, flags);
-		smp_mb__after_spinlock(); // Order updates vs. GP.
-		list = rtp->cbs_head;
-		rtp->cbs_head = NULL;
-		rtp->cbs_tail = &rtp->cbs_head;
-		raw_spin_unlock_irqrestore(&rtp->cbs_lock, flags);
-
 		/* If there were none, wait a bit and start over. */
-		if (!list) {
-			wait_event_interruptible(rtp->cbs_wq,
-						 READ_ONCE(rtp->cbs_head));
-			if (!rtp->cbs_head) {
-				WARN_ON(signal_pending(current));
-				set_tasks_gp_state(rtp, RTGS_WAIT_WAIT_CBS);
-				schedule_timeout_idle(HZ/10);
-			}
-			continue;
+		wait_event_idle(rtp->cbs_wq, (needgpcb = rcu_tasks_need_gpcb(rtp)));
+
+		if (needgpcb & 0x2) {
+			// Wait for one grace period.
+			set_tasks_gp_state(rtp, RTGS_WAIT_GP);
+			rtp->gp_start = jiffies;
+			rcu_seq_start(&rtp->tasks_gp_seq);
+			rtp->gp_func(rtp);
+			rcu_seq_end(&rtp->tasks_gp_seq);
 		}
 
-		// Wait for one grace period.
-		set_tasks_gp_state(rtp, RTGS_WAIT_GP);
-		rtp->gp_start = jiffies;
-		rtp->gp_func(rtp);
-		rtp->n_gps++;
-
-		/* Invoke the callbacks. */
+		/* Invoke callbacks. */
 		set_tasks_gp_state(rtp, RTGS_INVOKE_CBS);
-		while (list) {
-			next = list->next;
-			local_bh_disable();
-			list->func(list);
-			local_bh_enable();
-			list = next;
-			cond_resched();
-		}
+		rcu_tasks_invoke_cbs(rtp, per_cpu_ptr(rtp->rtpcpu, 0));
+
 		/* Paranoid sleep to keep this from entering a tight loop */
 		schedule_timeout_idle(rtp->gp_sleep);
 	}
@@ -279,14 +564,15 @@ static void __init rcu_tasks_bootup_oddness(void)
 /* Dump out rcutorture-relevant state common to all RCU-tasks flavors. */
 static void show_rcu_tasks_generic_gp_kthread(struct rcu_tasks *rtp, char *s)
 {
+	struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, 0); // for_each...
 	pr_info("%s: %s(%d) since %lu g:%lu i:%lu/%lu %c%c %s\n",
 		rtp->kname,
 		tasks_gp_state_getname(rtp), data_race(rtp->gp_state),
 		jiffies - data_race(rtp->gp_jiffies),
-		data_race(rtp->n_gps),
+		data_race(rcu_seq_current(&rtp->tasks_gp_seq)),
 		data_race(rtp->n_ipis_fails), data_race(rtp->n_ipis),
 		".k"[!!data_race(rtp->kthread_ptr)],
-		".C"[!!data_race(rtp->cbs_head)],
+		".C"[!data_race(rcu_segcblist_empty(&rtpcp->cblist))],
 		s);
 }
 #endif // #ifndef CONFIG_TINY_RCU
@@ -411,10 +697,10 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
 // exit_tasks_rcu_finish() functions begin and end, respectively, the SRCU
 // read-side critical sections waited for by rcu_tasks_postscan().
 //
-// Pre-grace-period update-side code is ordered before the grace via the
-// ->cbs_lock and the smp_mb__after_spinlock().  Pre-grace-period read-side
-// code is ordered before the grace period via synchronize_rcu() call
-// in rcu_tasks_pregp_step() and by the scheduler's locks and interrupt
+// Pre-grace-period update-side code is ordered before the grace
+// via the raw_spin_lock.*rcu_node().  Pre-grace-period read-side code
+// is ordered before the grace period via synchronize_rcu() call in
+// rcu_tasks_pregp_step() and by the scheduler's locks and interrupt
 // disabling.
 
 /* Pre-grace-period preparation. */
@@ -586,13 +872,13 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_tasks);
  */
 void rcu_barrier_tasks(void)
 {
-	/* There is only one callback queue, so this is easy.  ;-) */
-	synchronize_rcu_tasks();
+	rcu_barrier_tasks_generic(&rcu_tasks);
 }
 EXPORT_SYMBOL_GPL(rcu_barrier_tasks);
 
 static int __init rcu_spawn_tasks_kthread(void)
 {
+	cblist_init_generic(&rcu_tasks);
 	rcu_tasks.gp_sleep = HZ / 10;
 	rcu_tasks.init_fract = HZ / 10;
 	rcu_tasks.pregp_func = rcu_tasks_pregp_step;
@@ -724,13 +1010,13 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_tasks_rude);
  */
 void rcu_barrier_tasks_rude(void)
 {
-	/* There is only one callback queue, so this is easy.  ;-) */
-	synchronize_rcu_tasks_rude();
+	rcu_barrier_tasks_generic(&rcu_tasks_rude);
 }
 EXPORT_SYMBOL_GPL(rcu_barrier_tasks_rude);
 
 static int __init rcu_spawn_tasks_rude_kthread(void)
 {
+	cblist_init_generic(&rcu_tasks_rude);
 	rcu_tasks_rude.gp_sleep = HZ / 10;
 	rcu_spawn_tasks_kthread_generic(&rcu_tasks_rude);
 	return 0;
@@ -1073,25 +1359,50 @@ static void rcu_tasks_trace_postscan(struct list_head *hop)
 	// Any tasks that exit after this point will set ->trc_reader_checked.
 }
 
+/* Communicate task state back to the RCU tasks trace stall warning request. */
+struct trc_stall_chk_rdr {
+	int nesting;
+	int ipi_to_cpu;
+	u8 needqs;
+};
+
+static int trc_check_slow_task(struct task_struct *t, void *arg)
+{
+	struct trc_stall_chk_rdr *trc_rdrp = arg;
+
+	if (task_curr(t))
+		return false; // It is running, so decline to inspect it.
+	trc_rdrp->nesting = READ_ONCE(t->trc_reader_nesting);
+	trc_rdrp->ipi_to_cpu = READ_ONCE(t->trc_ipi_to_cpu);
+	trc_rdrp->needqs = READ_ONCE(t->trc_reader_special.b.need_qs);
+	return true;
+}
+
 /* Show the state of a task stalling the current RCU tasks trace GP. */
 static void show_stalled_task_trace(struct task_struct *t, bool *firstreport)
 {
 	int cpu;
+	struct trc_stall_chk_rdr trc_rdr;
+	bool is_idle_tsk = is_idle_task(t);
 
 	if (*firstreport) {
 		pr_err("INFO: rcu_tasks_trace detected stalls on tasks:\n");
 		*firstreport = false;
 	}
-	// FIXME: This should attempt to use try_invoke_on_nonrunning_task().
 	cpu = task_cpu(t);
-	pr_alert("P%d: %c%c%c nesting: %d%c cpu: %d\n",
-		 t->pid,
-		 ".I"[READ_ONCE(t->trc_ipi_to_cpu) >= 0],
-		 ".i"[is_idle_task(t)],
-		 ".N"[cpu >= 0 && tick_nohz_full_cpu(cpu)],
-		 READ_ONCE(t->trc_reader_nesting),
-		 " N"[!!READ_ONCE(t->trc_reader_special.b.need_qs)],
-		 cpu);
+	if (!task_call_func(t, trc_check_slow_task, &trc_rdr))
+		pr_alert("P%d: %c\n",
+			 t->pid,
+			 ".i"[is_idle_tsk]);
+	else
+		pr_alert("P%d: %c%c%c nesting: %d%c cpu: %d\n",
+			 t->pid,
+			 ".I"[trc_rdr.ipi_to_cpu >= 0],
+			 ".i"[is_idle_tsk],
+			 ".N"[cpu >= 0 && tick_nohz_full_cpu(cpu)],
+			 trc_rdr.nesting,
+			 " N"[!!trc_rdr.needqs],
+			 cpu);
 	sched_show_task(t);
 }
 
@@ -1121,7 +1432,8 @@ static void check_all_holdout_tasks_trace(struct list_head *hop,
 			trc_wait_for_one_reader(t, hop);
 
 		// If check succeeded, remove this task from the list.
-		if (READ_ONCE(t->trc_reader_checked))
+		if (smp_load_acquire(&t->trc_ipi_to_cpu) == -1 &&
+		    READ_ONCE(t->trc_reader_checked))
 			trc_del_holdout(t);
 		else if (needreport)
 			show_stalled_task_trace(t, firstreport);
@@ -1156,7 +1468,7 @@ static void rcu_tasks_trace_postgp(struct rcu_tasks *rtp)
 	// Yes, this assumes that CPUs process IPIs in order.  If that ever
 	// changes, there will need to be a recheck and/or timed wait.
 	for_each_online_cpu(cpu)
-		if (smp_load_acquire(per_cpu_ptr(&trc_ipi_to_cpu, cpu)))
+		if (WARN_ON_ONCE(smp_load_acquire(per_cpu_ptr(&trc_ipi_to_cpu, cpu))))
 			smp_call_function_single(cpu, rcu_tasks_trace_empty_fn, NULL, 1);
 
 	// Remove the safety count.
@@ -1256,13 +1568,13 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_tasks_trace);
  */
 void rcu_barrier_tasks_trace(void)
 {
-	/* There is only one callback queue, so this is easy.  ;-) */
-	synchronize_rcu_tasks_trace();
+	rcu_barrier_tasks_generic(&rcu_tasks_trace);
 }
 EXPORT_SYMBOL_GPL(rcu_barrier_tasks_trace);
 
 static int __init rcu_spawn_tasks_trace_kthread(void)
 {
+	cblist_init_generic(&rcu_tasks_trace);
 	if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) {
 		rcu_tasks_trace.gp_sleep = HZ / 10;
 		rcu_tasks_trace.init_fract = HZ / 10;
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index ef8d36f580fc..a4c25a6283b0 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -79,7 +79,7 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = {
 	.dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE,
 	.dynticks = ATOMIC_INIT(1),
 #ifdef CONFIG_RCU_NOCB_CPU
-	.cblist.flags = SEGCBLIST_SOFTIRQ_ONLY,
+	.cblist.flags = SEGCBLIST_RCU_CORE,
 #endif
 };
 static struct rcu_state rcu_state = {
@@ -624,7 +624,6 @@ static noinstr void rcu_eqs_enter(bool user)
 	instrumentation_begin();
 	trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
-	rcu_prepare_for_idle();
 	rcu_preempt_deferred_qs(current);
 
 	// instrumentation for the noinstr rcu_dynticks_eqs_enter()
@@ -768,9 +767,6 @@ noinstr void rcu_nmi_exit(void)
 	trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks));
 	WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */
 
-	if (!in_nmi())
-		rcu_prepare_for_idle();
-
 	// instrumentation for the noinstr rcu_dynticks_eqs_enter()
 	instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
 	instrumentation_end();
@@ -872,7 +868,6 @@ static void noinstr rcu_eqs_exit(bool user)
 	// instrumentation for the noinstr rcu_dynticks_eqs_exit()
 	instrument_atomic_write(&rdp->dynticks, sizeof(rdp->dynticks));
 
-	rcu_cleanup_after_idle();
 	trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks));
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current));
 	WRITE_ONCE(rdp->dynticks_nesting, 1);
@@ -1014,12 +1009,6 @@ noinstr void rcu_nmi_enter(void)
 		rcu_dynticks_eqs_exit();
 		// ... but is watching here.
 
-		if (!in_nmi()) {
-			instrumentation_begin();
-			rcu_cleanup_after_idle();
-			instrumentation_end();
-		}
-
 		instrumentation_begin();
 		// instrumentation for the noinstr rcu_dynticks_curr_cpu_in_eqs()
 		instrument_atomic_read(&rdp->dynticks, sizeof(rdp->dynticks));
@@ -1087,6 +1076,24 @@ void rcu_irq_enter_irqson(void)
 }
 
 /*
+ * Check to see if any future non-offloaded RCU-related work will need
+ * to be done by the current CPU, even if none need be done immediately,
+ * returning 1 if so.  This function is part of the RCU implementation;
+ * it is -not- an exported member of the RCU API.  This is used by
+ * the idle-entry code to figure out whether it is safe to disable the
+ * scheduler-clock interrupt.
+ *
+ * Just check whether or not this CPU has non-offloaded RCU callbacks
+ * queued.
+ */
+int rcu_needs_cpu(u64 basemono, u64 *nextevt)
+{
+	*nextevt = KTIME_MAX;
+	return !rcu_segcblist_empty(&this_cpu_ptr(&rcu_data)->cblist) &&
+		!rcu_rdp_is_offloaded(this_cpu_ptr(&rcu_data));
+}
+
+/*
  * If any sort of urgency was applied to the current CPU (for example,
  * the scheduler-clock interrupt was enabled on a nohz_full CPU) in order
  * to get to a quiescent state, disable it.
@@ -1467,7 +1474,7 @@ static void rcu_gp_kthread_wake(void)
 {
 	struct task_struct *t = READ_ONCE(rcu_state.gp_kthread);
 
-	if ((current == t && !in_irq() && !in_serving_softirq()) ||
+	if ((current == t && !in_hardirq() && !in_serving_softirq()) ||
 	    !READ_ONCE(rcu_state.gp_flags) || !t)
 		return;
 	WRITE_ONCE(rcu_state.gp_wake_time, jiffies);
@@ -1590,10 +1597,11 @@ static void __maybe_unused rcu_advance_cbs_nowake(struct rcu_node *rnp,
 						  struct rcu_data *rdp)
 {
 	rcu_lockdep_assert_cblist_protected(rdp);
-	if (!rcu_seq_state(rcu_seq_current(&rnp->gp_seq)) ||
-	    !raw_spin_trylock_rcu_node(rnp))
+	if (!rcu_seq_state(rcu_seq_current(&rnp->gp_seq)) || !raw_spin_trylock_rcu_node(rnp))
 		return;
-	WARN_ON_ONCE(rcu_advance_cbs(rnp, rdp));
+	// The grace period cannot end while we hold the rcu_node lock.
+	if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq)))
+		WARN_ON_ONCE(rcu_advance_cbs(rnp, rdp));
 	raw_spin_unlock_rcu_node(rnp);
 }
 
@@ -2277,7 +2285,7 @@ rcu_report_qs_rdp(struct rcu_data *rdp)
 	unsigned long flags;
 	unsigned long mask;
 	bool needwake = false;
-	const bool offloaded = rcu_rdp_is_offloaded(rdp);
+	bool needacc = false;
 	struct rcu_node *rnp;
 
 	WARN_ON_ONCE(rdp->cpu != smp_processor_id());
@@ -2304,15 +2312,30 @@ rcu_report_qs_rdp(struct rcu_data *rdp)
 		/*
 		 * This GP can't end until cpu checks in, so all of our
 		 * callbacks can be processed during the next GP.
+		 *
+		 * NOCB kthreads have their own way to deal with that...
 		 */
-		if (!offloaded)
+		if (!rcu_rdp_is_offloaded(rdp)) {
 			needwake = rcu_accelerate_cbs(rnp, rdp);
+		} else if (!rcu_segcblist_completely_offloaded(&rdp->cblist)) {
+			/*
+			 * ...but NOCB kthreads may miss or delay callbacks acceleration
+			 * if in the middle of a (de-)offloading process.
+			 */
+			needacc = true;
+		}
 
 		rcu_disable_urgency_upon_qs(rdp);
 		rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags);
 		/* ^^^ Released rnp->lock */
 		if (needwake)
 			rcu_gp_kthread_wake();
+
+		if (needacc) {
+			rcu_nocb_lock_irqsave(rdp, flags);
+			rcu_accelerate_cbs_unlocked(rnp, rdp);
+			rcu_nocb_unlock_irqrestore(rdp, flags);
+		}
 	}
 }
 
@@ -2444,7 +2467,6 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	int div;
 	bool __maybe_unused empty;
 	unsigned long flags;
-	const bool offloaded = rcu_rdp_is_offloaded(rdp);
 	struct rcu_head *rhp;
 	struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl);
 	long bl, count = 0;
@@ -2462,18 +2484,17 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	}
 
 	/*
-	 * Extract the list of ready callbacks, disabling to prevent
+	 * Extract the list of ready callbacks, disabling IRQs to prevent
 	 * races with call_rcu() from interrupt handlers.  Leave the
 	 * callback counts, as rcu_barrier() needs to be conservative.
 	 */
-	local_irq_save(flags);
-	rcu_nocb_lock(rdp);
+	rcu_nocb_lock_irqsave(rdp, flags);
 	WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
 	pending = rcu_segcblist_n_cbs(&rdp->cblist);
 	div = READ_ONCE(rcu_divisor);
 	div = div < 0 ? 7 : div > sizeof(long) * 8 - 2 ? sizeof(long) * 8 - 2 : div;
 	bl = max(rdp->blimit, pending >> div);
-	if (unlikely(bl > 100)) {
+	if (in_serving_softirq() && unlikely(bl > 100)) {
 		long rrn = READ_ONCE(rcu_resched_ns);
 
 		rrn = rrn < NSEC_PER_MSEC ? NSEC_PER_MSEC : rrn > NSEC_PER_SEC ? NSEC_PER_SEC : rrn;
@@ -2482,7 +2503,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	trace_rcu_batch_start(rcu_state.name,
 			      rcu_segcblist_n_cbs(&rdp->cblist), bl);
 	rcu_segcblist_extract_done_cbs(&rdp->cblist, &rcl);
-	if (offloaded)
+	if (rcu_rdp_is_offloaded(rdp))
 		rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist);
 
 	trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCbDequeued"));
@@ -2510,18 +2531,21 @@ static void rcu_do_batch(struct rcu_data *rdp)
 		/*
 		 * Stop only if limit reached and CPU has something to do.
 		 */
-		if (count >= bl && !offloaded &&
-		    (need_resched() ||
-		     (!is_idle_task(current) && !rcu_is_callbacks_kthread())))
-			break;
-		if (unlikely(tlimit)) {
-			/* only call local_clock() every 32 callbacks */
-			if (likely((count & 31) || local_clock() < tlimit))
-				continue;
-			/* Exceeded the time limit, so leave. */
-			break;
-		}
-		if (!in_serving_softirq()) {
+		if (in_serving_softirq()) {
+			if (count >= bl && (need_resched() || !is_idle_task(current)))
+				break;
+			/*
+			 * Make sure we don't spend too much time here and deprive other
+			 * softirq vectors of CPU cycles.
+			 */
+			if (unlikely(tlimit)) {
+				/* only call local_clock() every 32 callbacks */
+				if (likely((count & 31) || local_clock() < tlimit))
+					continue;
+				/* Exceeded the time limit, so leave. */
+				break;
+			}
+		} else {
 			local_bh_enable();
 			lockdep_assert_irqs_enabled();
 			cond_resched_tasks_rcu_qs();
@@ -2530,8 +2554,7 @@ static void rcu_do_batch(struct rcu_data *rdp)
 		}
 	}
 
-	local_irq_save(flags);
-	rcu_nocb_lock(rdp);
+	rcu_nocb_lock_irqsave(rdp, flags);
 	rdp->n_cbs_invoked += count;
 	trace_rcu_batch_end(rcu_state.name, count, !!rcl.head, need_resched(),
 			    is_idle_task(current), rcu_is_callbacks_kthread());
@@ -2565,9 +2588,6 @@ static void rcu_do_batch(struct rcu_data *rdp)
 
 	rcu_nocb_unlock_irqrestore(rdp, flags);
 
-	/* Re-invoke RCU core processing if there are callbacks remaining. */
-	if (!offloaded && rcu_segcblist_ready_cbs(&rdp->cblist))
-		invoke_rcu_core();
 	tick_dep_clear_task(current, TICK_DEP_BIT_RCU);
 }
 
@@ -2706,6 +2726,23 @@ static __latent_entropy void rcu_core(void)
 	unsigned long flags;
 	struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
 	struct rcu_node *rnp = rdp->mynode;
+	/*
+	 * On RT rcu_core() can be preempted when IRQs aren't disabled.
+	 * Therefore this function can race with concurrent NOCB (de-)offloading
+	 * on this CPU and the below condition must be considered volatile.
+	 * However if we race with:
+	 *
+	 * _ Offloading:   In the worst case we accelerate or process callbacks
+	 *                 concurrently with NOCB kthreads. We are guaranteed to
+	 *                 call rcu_nocb_lock() if that happens.
+	 *
+	 * _ Deoffloading: In the worst case we miss callbacks acceleration or
+	 *                 processing. This is fine because the early stage
+	 *                 of deoffloading invokes rcu_core() after setting
+	 *                 SEGCBLIST_RCU_CORE. So we guarantee that we'll process
+	 *                 what could have been dismissed without the need to wait
+	 *                 for the next rcu_pending() check in the next jiffy.
+	 */
 	const bool do_batch = !rcu_segcblist_completely_offloaded(&rdp->cblist);
 
 	if (cpu_is_offline(smp_processor_id()))
@@ -2714,7 +2751,7 @@ static __latent_entropy void rcu_core(void)
 	WARN_ON_ONCE(!rdp->beenonline);
 
 	/* Report any deferred quiescent states if preemption enabled. */
-	if (!(preempt_count() & PREEMPT_MASK)) {
+	if (IS_ENABLED(CONFIG_PREEMPT_COUNT) && (!(preempt_count() & PREEMPT_MASK))) {
 		rcu_preempt_deferred_qs(current);
 	} else if (rcu_preempt_need_deferred_qs(current)) {
 		set_tsk_need_resched(current);
@@ -2737,8 +2774,12 @@ static __latent_entropy void rcu_core(void)
 
 	/* If there are callbacks ready, invoke them. */
 	if (do_batch && rcu_segcblist_ready_cbs(&rdp->cblist) &&
-	    likely(READ_ONCE(rcu_scheduler_fully_active)))
+	    likely(READ_ONCE(rcu_scheduler_fully_active))) {
 		rcu_do_batch(rdp);
+		/* Re-invoke RCU core processing if there are callbacks remaining. */
+		if (rcu_segcblist_ready_cbs(&rdp->cblist))
+			invoke_rcu_core();
+	}
 
 	/* Do any needed deferred wakeups of rcuo kthreads. */
 	do_nocb_deferred_wakeup(rdp);
@@ -2982,7 +3023,7 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func)
 	head->func = func;
 	head->next = NULL;
 	local_irq_save(flags);
-	kasan_record_aux_stack(head);
+	kasan_record_aux_stack_noalloc(head);
 	rdp = this_cpu_ptr(&rcu_data);
 
 	/* Add the callback to our list. */
@@ -3547,7 +3588,7 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 		return;
 	}
 
-	kasan_record_aux_stack(ptr);
+	kasan_record_aux_stack_noalloc(ptr);
 	success = add_ptr_to_bulk_krc_lock(&krcp, &flags, ptr, !head);
 	if (!success) {
 		run_page_cache_worker(krcp);
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 305cf6aeb408..486fc901bd08 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -157,7 +157,6 @@ struct rcu_data {
 	bool		core_needs_qs;	/* Core waits for quiescent state. */
 	bool		beenonline;	/* CPU online at least once. */
 	bool		gpwrap;		/* Possible ->gp_seq wrap. */
-	bool		exp_deferred_qs; /* This CPU awaiting a deferred QS? */
 	bool		cpu_started;	/* RCU watching this onlining CPU. */
 	struct rcu_node *mynode;	/* This CPU's leaf of hierarchy */
 	unsigned long grpmask;		/* Mask to apply to leaf qsmask. */
@@ -189,11 +188,6 @@ struct rcu_data {
 	bool rcu_urgent_qs;		/* GP old need light quiescent state. */
 	bool rcu_forced_tick;		/* Forced tick to provide QS. */
 	bool rcu_forced_tick_exp;	/*   ... provide QS to expedited GP. */
-#ifdef CONFIG_RCU_FAST_NO_HZ
-	unsigned long last_accelerate;	/* Last jiffy CBs were accelerated. */
-	unsigned long last_advance_all;	/* Last jiffy CBs were all advanced. */
-	int tick_nohz_enabled_snap;	/* Previously seen value from sysfs. */
-#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */
 
 	/* 4) rcu_barrier(), OOM callbacks, and expediting. */
 	struct rcu_head barrier_head;
@@ -227,8 +221,11 @@ struct rcu_data {
 	struct swait_queue_head nocb_gp_wq; /* For nocb kthreads to sleep on. */
 	bool nocb_cb_sleep;		/* Is the nocb CB thread asleep? */
 	struct task_struct *nocb_cb_kthread;
-	struct rcu_data *nocb_next_cb_rdp;
-					/* Next rcu_data in wakeup chain. */
+	struct list_head nocb_head_rdp; /*
+					 * Head of rcu_data list in wakeup chain,
+					 * if rdp_gp.
+					 */
+	struct list_head nocb_entry_rdp; /* rcu_data node in wakeup chain. */
 
 	/* The following fields are used by CB kthread, hence new cacheline. */
 	struct rcu_data *nocb_gp_rdp ____cacheline_internodealigned_in_smp;
@@ -419,8 +416,6 @@ static bool rcu_is_callbacks_kthread(void);
 static void rcu_cpu_kthread_setup(unsigned int cpu);
 static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp);
 static void __init rcu_spawn_boost_kthreads(void);
-static void rcu_cleanup_after_idle(void);
-static void rcu_prepare_for_idle(void);
 static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
 static bool rcu_preempt_need_deferred_qs(struct task_struct *t);
 static void rcu_preempt_deferred_qs(struct task_struct *t);
@@ -447,12 +442,16 @@ static void rcu_nocb_unlock_irqrestore(struct rcu_data *rdp,
 static void rcu_lockdep_assert_cblist_protected(struct rcu_data *rdp);
 #ifdef CONFIG_RCU_NOCB_CPU
 static void __init rcu_organize_nocb_kthreads(void);
-#define rcu_nocb_lock_irqsave(rdp, flags)				\
-do {									\
-	if (!rcu_segcblist_is_offloaded(&(rdp)->cblist))		\
-		local_irq_save(flags);					\
-	else								\
-		raw_spin_lock_irqsave(&(rdp)->nocb_lock, (flags));	\
+
+/*
+ * Disable IRQs before checking offloaded state so that local
+ * locking is safe against concurrent de-offloading.
+ */
+#define rcu_nocb_lock_irqsave(rdp, flags)			\
+do {								\
+	local_irq_save(flags);					\
+	if (rcu_segcblist_is_offloaded(&(rdp)->cblist))	\
+		raw_spin_lock(&(rdp)->nocb_lock);		\
 } while (0)
 #else /* #ifdef CONFIG_RCU_NOCB_CPU */
 #define rcu_nocb_lock_irqsave(rdp, flags) local_irq_save(flags)
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index f3947c49eee7..237a79989aba 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -255,7 +255,7 @@ static void rcu_report_exp_cpu_mult(struct rcu_node *rnp,
  */
 static void rcu_report_exp_rdp(struct rcu_data *rdp)
 {
-	WRITE_ONCE(rdp->exp_deferred_qs, false);
+	WRITE_ONCE(rdp->cpu_no_qs.b.exp, false);
 	rcu_report_exp_cpu_mult(rdp->mynode, rdp->grpmask, true);
 }
 
@@ -387,6 +387,7 @@ retry_ipi:
 			continue;
 		}
 		if (get_cpu() == cpu) {
+			mask_ofl_test |= mask;
 			put_cpu();
 			continue;
 		}
@@ -506,7 +507,10 @@ static void synchronize_rcu_expedited_wait(void)
 				if (rdp->rcu_forced_tick_exp)
 					continue;
 				rdp->rcu_forced_tick_exp = true;
-				tick_dep_set_cpu(cpu, TICK_DEP_BIT_RCU_EXP);
+				preempt_disable();
+				if (cpu_online(cpu))
+					tick_dep_set_cpu(cpu, TICK_DEP_BIT_RCU_EXP);
+				preempt_enable();
 			}
 		}
 		j = READ_ONCE(jiffies_till_first_fqs);
@@ -655,7 +659,7 @@ static void rcu_exp_handler(void *unused)
 		    rcu_dynticks_curr_cpu_in_eqs()) {
 			rcu_report_exp_rdp(rdp);
 		} else {
-			rdp->exp_deferred_qs = true;
+			WRITE_ONCE(rdp->cpu_no_qs.b.exp, true);
 			set_tsk_need_resched(t);
 			set_preempt_need_resched();
 		}
@@ -677,7 +681,7 @@ static void rcu_exp_handler(void *unused)
 	if (depth > 0) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->expmask & rdp->grpmask) {
-			rdp->exp_deferred_qs = true;
+			WRITE_ONCE(rdp->cpu_no_qs.b.exp, true);
 			t->rcu_read_unlock_special.b.exp_hint = true;
 		}
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -759,7 +763,7 @@ static void sync_sched_exp_online_cleanup(int cpu)
 	my_cpu = get_cpu();
 	/* Quiescent state either not needed or already requested, leave. */
 	if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) ||
-	    rdp->cpu_no_qs.b.exp) {
+	    READ_ONCE(rdp->cpu_no_qs.b.exp)) {
 		put_cpu();
 		return;
 	}
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index 368ef7b9af4f..eeafb546a7a0 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -60,16 +60,22 @@ static inline bool rcu_current_is_nocb_kthread(struct rcu_data *rdp)
  * Parse the boot-time rcu_nocb_mask CPU list from the kernel parameters.
  * If the list is invalid, a warning is emitted and all CPUs are offloaded.
  */
+
+static bool rcu_nocb_is_setup;
+
 static int __init rcu_nocb_setup(char *str)
 {
 	alloc_bootmem_cpumask_var(&rcu_nocb_mask);
-	if (cpulist_parse(str, rcu_nocb_mask)) {
-		pr_warn("rcu_nocbs= bad CPU range, all CPUs set\n");
-		cpumask_setall(rcu_nocb_mask);
+	if (*str == '=') {
+		if (cpulist_parse(++str, rcu_nocb_mask)) {
+			pr_warn("rcu_nocbs= bad CPU range, all CPUs set\n");
+			cpumask_setall(rcu_nocb_mask);
+		}
 	}
+	rcu_nocb_is_setup = true;
 	return 1;
 }
-__setup("rcu_nocbs=", rcu_nocb_setup);
+__setup("rcu_nocbs", rcu_nocb_setup);
 
 static int __init parse_rcu_nocb_poll(char *arg)
 {
@@ -625,7 +631,21 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 	 * and the global grace-period kthread are awakened if needed.
 	 */
 	WARN_ON_ONCE(my_rdp->nocb_gp_rdp != my_rdp);
-	for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_cb_rdp) {
+	/*
+	 * An rcu_data structure is removed from the list after its
+	 * CPU is de-offloaded and added to the list before that CPU is
+	 * (re-)offloaded.  If the following loop happens to be referencing
+	 * that rcu_data structure during the time that the corresponding
+	 * CPU is de-offloaded and then immediately re-offloaded, this
+	 * loop's rdp pointer will be carried to the end of the list by
+	 * the resulting pair of list operations.  This can cause the loop
+	 * to skip over some of the rcu_data structures that were supposed
+	 * to have been scanned.  Fortunately a new iteration through the
+	 * entire loop is forced after a given CPU's rcu_data structure
+	 * is added to the list, so the skipped-over rcu_data structures
+	 * won't be ignored for long.
+	 */
+	list_for_each_entry_rcu(rdp, &my_rdp->nocb_head_rdp, nocb_entry_rdp, 1) {
 		bool needwake_state = false;
 
 		if (!nocb_gp_enabled_cb(rdp))
@@ -789,6 +809,18 @@ static void nocb_cb_wait(struct rcu_data *rdp)
 	bool can_sleep = true;
 	struct rcu_node *rnp = rdp->mynode;
 
+	do {
+		swait_event_interruptible_exclusive(rdp->nocb_cb_wq,
+						    nocb_cb_wait_cond(rdp));
+
+		// VVV Ensure CB invocation follows _sleep test.
+		if (smp_load_acquire(&rdp->nocb_cb_sleep)) { // ^^^
+			WARN_ON(signal_pending(current));
+			trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WokeEmpty"));
+		}
+	} while (!nocb_cb_can_run(rdp));
+
+
 	local_irq_save(flags);
 	rcu_momentary_dyntick_idle();
 	local_irq_restore(flags);
@@ -841,17 +873,6 @@ static void nocb_cb_wait(struct rcu_data *rdp)
 
 	if (needwake_state)
 		swake_up_one(&rdp->nocb_state_wq);
-
-	do {
-		swait_event_interruptible_exclusive(rdp->nocb_cb_wq,
-						    nocb_cb_wait_cond(rdp));
-
-		// VVV Ensure CB invocation follows _sleep test.
-		if (smp_load_acquire(&rdp->nocb_cb_sleep)) { // ^^^
-			WARN_ON(signal_pending(current));
-			trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WokeEmpty"));
-		}
-	} while (!nocb_cb_can_run(rdp));
 }
 
 /*
@@ -990,22 +1011,33 @@ static long rcu_nocb_rdp_deoffload(void *arg)
 	 * will refuse to put anything into the bypass.
 	 */
 	WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies));
+	/*
+	 * Start with invoking rcu_core() early. This way if the current thread
+	 * happens to preempt an ongoing call to rcu_core() in the middle,
+	 * leaving some work dismissed because rcu_core() still thinks the rdp is
+	 * completely offloaded, we are guaranteed a nearby future instance of
+	 * rcu_core() to catch up.
+	 */
+	rcu_segcblist_set_flags(cblist, SEGCBLIST_RCU_CORE);
+	invoke_rcu_core();
 	ret = rdp_offload_toggle(rdp, false, flags);
 	swait_event_exclusive(rdp->nocb_state_wq,
 			      !rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB |
 							SEGCBLIST_KTHREAD_GP));
+	/* Stop nocb_gp_wait() from iterating over this structure. */
+	list_del_rcu(&rdp->nocb_entry_rdp);
 	/*
 	 * Lock one last time to acquire latest callback updates from kthreads
 	 * so we can later handle callbacks locally without locking.
 	 */
 	rcu_nocb_lock_irqsave(rdp, flags);
 	/*
-	 * Theoretically we could set SEGCBLIST_SOFTIRQ_ONLY after the nocb
+	 * Theoretically we could clear SEGCBLIST_LOCKING after the nocb
 	 * lock is released but how about being paranoid for once?
 	 */
-	rcu_segcblist_set_flags(cblist, SEGCBLIST_SOFTIRQ_ONLY);
+	rcu_segcblist_clear_flags(cblist, SEGCBLIST_LOCKING);
 	/*
-	 * With SEGCBLIST_SOFTIRQ_ONLY, we can't use
+	 * Without SEGCBLIST_LOCKING, we can't use
 	 * rcu_nocb_unlock_irqrestore() anymore.
 	 */
 	raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
@@ -1057,15 +1089,26 @@ static long rcu_nocb_rdp_offload(void *arg)
 		return -EINVAL;
 
 	pr_info("Offloading %d\n", rdp->cpu);
+
+	/*
+	 * Cause future nocb_gp_wait() invocations to iterate over
+	 * structure, resetting ->nocb_gp_sleep and waking up the related
+	 * "rcuog".  Since nocb_gp_wait() in turn locks ->nocb_gp_lock
+	 * before setting ->nocb_gp_sleep again, we are guaranteed to
+	 * iterate this newly added structure before "rcuog" goes to
+	 * sleep again.
+	 */
+	list_add_tail_rcu(&rdp->nocb_entry_rdp, &rdp->nocb_gp_rdp->nocb_head_rdp);
+
 	/*
-	 * Can't use rcu_nocb_lock_irqsave() while we are in
-	 * SEGCBLIST_SOFTIRQ_ONLY mode.
+	 * Can't use rcu_nocb_lock_irqsave() before SEGCBLIST_LOCKING
+	 * is set.
 	 */
 	raw_spin_lock_irqsave(&rdp->nocb_lock, flags);
 
 	/*
 	 * We didn't take the nocb lock while working on the
-	 * rdp->cblist in SEGCBLIST_SOFTIRQ_ONLY mode.
+	 * rdp->cblist with SEGCBLIST_LOCKING cleared (pure softirq/rcuc mode).
 	 * Every modifications that have been done previously on
 	 * rdp->cblist must be visible remotely by the nocb kthreads
 	 * upon wake up after reading the cblist flags.
@@ -1084,6 +1127,14 @@ static long rcu_nocb_rdp_offload(void *arg)
 			      rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB) &&
 			      rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_GP));
 
+	/*
+	 * All kthreads are ready to work, we can finally relieve rcu_core() and
+	 * enable nocb bypass.
+	 */
+	rcu_nocb_lock_irqsave(rdp, flags);
+	rcu_segcblist_clear_flags(cblist, SEGCBLIST_RCU_CORE);
+	rcu_nocb_unlock_irqrestore(rdp, flags);
+
 	return ret;
 }
 
@@ -1122,13 +1173,17 @@ void __init rcu_init_nohz(void)
 		need_rcu_nocb_mask = true;
 #endif /* #if defined(CONFIG_NO_HZ_FULL) */
 
-	if (!cpumask_available(rcu_nocb_mask) && need_rcu_nocb_mask) {
-		if (!zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL)) {
-			pr_info("rcu_nocb_mask allocation failed, callback offloading disabled.\n");
-			return;
+	if (need_rcu_nocb_mask) {
+		if (!cpumask_available(rcu_nocb_mask)) {
+			if (!zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL)) {
+				pr_info("rcu_nocb_mask allocation failed, callback offloading disabled.\n");
+				return;
+			}
 		}
+		rcu_nocb_is_setup = true;
 	}
-	if (!cpumask_available(rcu_nocb_mask))
+
+	if (!rcu_nocb_is_setup)
 		return;
 
 #if defined(CONFIG_NO_HZ_FULL)
@@ -1154,8 +1209,8 @@ void __init rcu_init_nohz(void)
 		if (rcu_segcblist_empty(&rdp->cblist))
 			rcu_segcblist_init(&rdp->cblist);
 		rcu_segcblist_offload(&rdp->cblist, true);
-		rcu_segcblist_set_flags(&rdp->cblist, SEGCBLIST_KTHREAD_CB);
-		rcu_segcblist_set_flags(&rdp->cblist, SEGCBLIST_KTHREAD_GP);
+		rcu_segcblist_set_flags(&rdp->cblist, SEGCBLIST_KTHREAD_CB | SEGCBLIST_KTHREAD_GP);
+		rcu_segcblist_clear_flags(&rdp->cblist, SEGCBLIST_RCU_CORE);
 	}
 	rcu_organize_nocb_kthreads();
 }
@@ -1178,17 +1233,17 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp)
  * rcuo CB kthread, spawn it.  Additionally, if the rcuo GP kthread
  * for this CPU's group has not yet been created, spawn it as well.
  */
-static void rcu_spawn_one_nocb_kthread(int cpu)
+static void rcu_spawn_cpu_nocb_kthread(int cpu)
 {
 	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 	struct rcu_data *rdp_gp;
 	struct task_struct *t;
 
-	/*
-	 * If this isn't a no-CBs CPU or if it already has an rcuo kthread,
-	 * then nothing to do.
-	 */
-	if (!rcu_is_nocb_cpu(cpu) || rdp->nocb_cb_kthread)
+	if (!rcu_scheduler_fully_active || !rcu_nocb_is_setup)
+		return;
+
+	/* If there already is an rcuo kthread, then nothing to do. */
+	if (rdp->nocb_cb_kthread)
 		return;
 
 	/* If we didn't spawn the GP kthread first, reorganize! */
@@ -1211,16 +1266,6 @@ static void rcu_spawn_one_nocb_kthread(int cpu)
 }
 
 /*
- * If the specified CPU is a no-CBs CPU that does not already have its
- * rcuo kthread, spawn it.
- */
-static void rcu_spawn_cpu_nocb_kthread(int cpu)
-{
-	if (rcu_scheduler_fully_active)
-		rcu_spawn_one_nocb_kthread(cpu);
-}
-
-/*
  * Once the scheduler is running, spawn rcuo kthreads for all online
  * no-CBs CPUs.  This assumes that the early_initcall()s happen before
  * non-boot CPUs come online -- if this changes, we will need to add
@@ -1230,8 +1275,10 @@ static void __init rcu_spawn_nocb_kthreads(void)
 {
 	int cpu;
 
-	for_each_online_cpu(cpu)
-		rcu_spawn_cpu_nocb_kthread(cpu);
+	if (rcu_nocb_is_setup) {
+		for_each_online_cpu(cpu)
+			rcu_spawn_cpu_nocb_kthread(cpu);
+	}
 }
 
 /* How many CB CPU IDs per GP kthread?  Default of -1 for sqrt(nr_cpu_ids). */
@@ -1251,7 +1298,6 @@ static void __init rcu_organize_nocb_kthreads(void)
 	int nl = 0;  /* Next GP kthread. */
 	struct rcu_data *rdp;
 	struct rcu_data *rdp_gp = NULL;  /* Suppress misguided gcc warn. */
-	struct rcu_data *rdp_prev = NULL;
 
 	if (!cpumask_available(rcu_nocb_mask))
 		return;
@@ -1265,14 +1311,14 @@ static void __init rcu_organize_nocb_kthreads(void)
 	 * Should the corresponding CPU come online in the future, then
 	 * we will spawn the needed set of rcu_nocb_kthread() kthreads.
 	 */
-	for_each_cpu(cpu, rcu_nocb_mask) {
+	for_each_possible_cpu(cpu) {
 		rdp = per_cpu_ptr(&rcu_data, cpu);
 		if (rdp->cpu >= nl) {
 			/* New GP kthread, set up for CBs & next GP. */
 			gotnocbs = true;
 			nl = DIV_ROUND_UP(rdp->cpu + 1, ls) * ls;
-			rdp->nocb_gp_rdp = rdp;
 			rdp_gp = rdp;
+			INIT_LIST_HEAD(&rdp->nocb_head_rdp);
 			if (dump_tree) {
 				if (!firsttime)
 					pr_cont("%s\n", gotnocbscbs
@@ -1285,12 +1331,12 @@ static void __init rcu_organize_nocb_kthreads(void)
 		} else {
 			/* Another CB kthread, link to previous GP kthread. */
 			gotnocbscbs = true;
-			rdp->nocb_gp_rdp = rdp_gp;
-			rdp_prev->nocb_next_cb_rdp = rdp;
 			if (dump_tree)
 				pr_cont(" %d", cpu);
 		}
-		rdp_prev = rdp;
+		rdp->nocb_gp_rdp = rdp_gp;
+		if (cpumask_test_cpu(cpu, rcu_nocb_mask))
+			list_add_tail(&rdp->nocb_entry_rdp, &rdp_gp->nocb_head_rdp);
 	}
 	if (gotnocbs && dump_tree)
 		pr_cont("%s\n", gotnocbscbs ? "" : " (self only)");
@@ -1352,6 +1398,7 @@ static void show_rcu_nocb_state(struct rcu_data *rdp)
 {
 	char bufw[20];
 	char bufr[20];
+	struct rcu_data *nocb_next_rdp;
 	struct rcu_segcblist *rsclp = &rdp->cblist;
 	bool waslocked;
 	bool wassleep;
@@ -1359,11 +1406,16 @@ static void show_rcu_nocb_state(struct rcu_data *rdp)
 	if (rdp->nocb_gp_rdp == rdp)
 		show_rcu_nocb_gp_state(rdp);
 
+	nocb_next_rdp = list_next_or_null_rcu(&rdp->nocb_gp_rdp->nocb_head_rdp,
+					      &rdp->nocb_entry_rdp,
+					      typeof(*rdp),
+					      nocb_entry_rdp);
+
 	sprintf(bufw, "%ld", rsclp->gp_seq[RCU_WAIT_TAIL]);
 	sprintf(bufr, "%ld", rsclp->gp_seq[RCU_NEXT_READY_TAIL]);
 	pr_info("   CB %d^%d->%d %c%c%c%c%c%c F%ld L%ld C%d %c%c%s%c%s%c%c q%ld %c CPU %d%s\n",
 		rdp->cpu, rdp->nocb_gp_rdp->cpu,
-		rdp->nocb_next_cb_rdp ? rdp->nocb_next_cb_rdp->cpu : -1,
+		nocb_next_rdp ? nocb_next_rdp->cpu : -1,
 		"kK"[!!rdp->nocb_cb_kthread],
 		"bB"[raw_spin_is_locked(&rdp->nocb_bypass_lock)],
 		"cC"[!!atomic_read(&rdp->nocb_lock_contended)],
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 5199559fbbf0..c5b45c2f68a1 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -16,7 +16,7 @@
 static bool rcu_rdp_is_offloaded(struct rcu_data *rdp)
 {
 	/*
-	 * In order to read the offloaded state of an rdp is a safe
+	 * In order to read the offloaded state of an rdp in a safe
 	 * and stable way and prevent from its value to be changed
 	 * under us, we must either hold the barrier mutex, the cpu
 	 * hotplug lock (read or write) or the nocb lock. Local
@@ -51,12 +51,10 @@ static void __init rcu_bootup_announce_oddness(void)
 			RCU_FANOUT);
 	if (rcu_fanout_exact)
 		pr_info("\tHierarchical RCU autobalancing is disabled.\n");
-	if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ))
-		pr_info("\tRCU dyntick-idle grace-period acceleration is enabled.\n");
 	if (IS_ENABLED(CONFIG_PROVE_RCU))
 		pr_info("\tRCU lockdep checking is enabled.\n");
 	if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD))
-		pr_info("\tRCU strict (and thus non-scalable) grace periods enabled.\n");
+		pr_info("\tRCU strict (and thus non-scalable) grace periods are enabled.\n");
 	if (RCU_NUM_LVLS >= 4)
 		pr_info("\tFour(or more)-level hierarchy is enabled.\n");
 	if (RCU_FANOUT_LEAF != 16)
@@ -88,13 +86,13 @@ static void __init rcu_bootup_announce_oddness(void)
 	if (rcu_kick_kthreads)
 		pr_info("\tKick kthreads if too-long grace period.\n");
 	if (IS_ENABLED(CONFIG_DEBUG_OBJECTS_RCU_HEAD))
-		pr_info("\tRCU callback double-/use-after-free debug enabled.\n");
+		pr_info("\tRCU callback double-/use-after-free debug is enabled.\n");
 	if (gp_preinit_delay)
 		pr_info("\tRCU debug GP pre-init slowdown %d jiffies.\n", gp_preinit_delay);
 	if (gp_init_delay)
 		pr_info("\tRCU debug GP init slowdown %d jiffies.\n", gp_init_delay);
 	if (gp_cleanup_delay)
-		pr_info("\tRCU debug GP init slowdown %d jiffies.\n", gp_cleanup_delay);
+		pr_info("\tRCU debug GP cleanup slowdown %d jiffies.\n", gp_cleanup_delay);
 	if (!use_softirq)
 		pr_info("\tRCU_SOFTIRQ processing moved to rcuc kthreads.\n");
 	if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG))
@@ -260,10 +258,10 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 	 * 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 && rdp->exp_deferred_qs)
+	if (blkd_state & RCU_EXP_BLKD && rdp->cpu_no_qs.b.exp)
 		rcu_report_exp_rdp(rdp);
 	else
-		WARN_ON_ONCE(rdp->exp_deferred_qs);
+		WARN_ON_ONCE(rdp->cpu_no_qs.b.exp);
 }
 
 /*
@@ -277,12 +275,16 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
  * current task, there might be any number of other tasks blocked while
  * in an RCU read-side critical section.
  *
+ * Unlike non-preemptible-RCU, quiescent state reports for expedited
+ * grace periods are handled separately via deferred quiescent states
+ * and context switch events.
+ *
  * Callers to this function must disable preemption.
  */
 static void rcu_qs(void)
 {
 	RCU_LOCKDEP_WARN(preemptible(), "rcu_qs() invoked with preemption enabled!!!\n");
-	if (__this_cpu_read(rcu_data.cpu_no_qs.s)) {
+	if (__this_cpu_read(rcu_data.cpu_no_qs.b.norm)) {
 		trace_rcu_grace_period(TPS("rcu_preempt"),
 				       __this_cpu_read(rcu_data.gp_seq),
 				       TPS("cpuqs"));
@@ -350,7 +352,7 @@ void rcu_note_context_switch(bool preempt)
 	 * means that we continue to block the current grace period.
 	 */
 	rcu_qs();
-	if (rdp->exp_deferred_qs)
+	if (rdp->cpu_no_qs.b.exp)
 		rcu_report_exp_rdp(rdp);
 	rcu_tasks_qs(current, preempt);
 	trace_rcu_utilization(TPS("End context switch"));
@@ -477,7 +479,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 	 */
 	special = t->rcu_read_unlock_special;
 	rdp = this_cpu_ptr(&rcu_data);
-	if (!special.s && !rdp->exp_deferred_qs) {
+	if (!special.s && !rdp->cpu_no_qs.b.exp) {
 		local_irq_restore(flags);
 		return;
 	}
@@ -497,7 +499,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 	 * tasks are handled when removing the task from the
 	 * blocked-tasks list below.
 	 */
-	if (rdp->exp_deferred_qs)
+	if (rdp->cpu_no_qs.b.exp)
 		rcu_report_exp_rdp(rdp);
 
 	/* Clean up if blocked during RCU read-side critical section. */
@@ -580,7 +582,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
  */
 static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 {
-	return (__this_cpu_read(rcu_data.exp_deferred_qs) ||
+	return (__this_cpu_read(rcu_data.cpu_no_qs.b.exp) ||
 		READ_ONCE(t->rcu_read_unlock_special.s)) &&
 	       rcu_preempt_depth() == 0;
 }
@@ -642,7 +644,7 @@ static void rcu_read_unlock_special(struct task_struct *t)
 			   (IS_ENABLED(CONFIG_RCU_BOOST) && irqs_were_disabled &&
 			    t->rcu_blocked_node);
 		// Need to defer quiescent state until everything is enabled.
-		if (use_softirq && (in_irq() || (expboost && !irqs_were_disabled))) {
+		if (use_softirq && (in_hardirq() || (expboost && !irqs_were_disabled))) {
 			// Using softirq, safe to awaken, and either the
 			// wakeup is free or there is either an expedited
 			// GP in flight or a potential need to deboost.
@@ -845,10 +847,8 @@ static void rcu_qs(void)
 	trace_rcu_grace_period(TPS("rcu_sched"),
 			       __this_cpu_read(rcu_data.gp_seq), TPS("cpuqs"));
 	__this_cpu_write(rcu_data.cpu_no_qs.b.norm, false);
-	if (!__this_cpu_read(rcu_data.cpu_no_qs.b.exp))
-		return;
-	__this_cpu_write(rcu_data.cpu_no_qs.b.exp, false);
-	rcu_report_exp_rdp(this_cpu_ptr(&rcu_data));
+	if (__this_cpu_read(rcu_data.cpu_no_qs.b.exp))
+		rcu_report_exp_rdp(this_cpu_ptr(&rcu_data));
 }
 
 /*
@@ -925,7 +925,18 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 {
 	return false;
 }
-static void rcu_preempt_deferred_qs(struct task_struct *t) { }
+
+// Except that we do need to respond to a request by an expedited grace
+// period for a quiescent state from this CPU.  Note that requests from
+// tasks are handled when removing the task from the blocked-tasks list
+// below.
+static void rcu_preempt_deferred_qs(struct task_struct *t)
+{
+	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+
+	if (rdp->cpu_no_qs.b.exp)
+		rcu_report_exp_rdp(rdp);
+}
 
 /*
  * Because there is no preemptible RCU, there can be no readers blocked,
@@ -1153,7 +1164,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
 /*
  * Create an RCU-boost kthread for the specified node if one does not
  * already exist.  We only create this kthread for preemptible RCU.
- * Returns zero if all is well, a negated errno otherwise.
  */
 static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
 {
@@ -1204,8 +1214,9 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu)
 		if ((mask & leaf_node_cpu_bit(rnp, cpu)) &&
 		    cpu != outgoingcpu)
 			cpumask_set_cpu(cpu, cm);
+	cpumask_and(cm, cm, housekeeping_cpumask(HK_FLAG_RCU));
 	if (cpumask_weight(cm) == 0)
-		cpumask_setall(cm);
+		cpumask_copy(cm, housekeeping_cpumask(HK_FLAG_RCU));
 	set_cpus_allowed_ptr(t, cm);
 	free_cpumask_var(cm);
 }
@@ -1253,201 +1264,6 @@ static void __init rcu_spawn_boost_kthreads(void)
 
 #endif /* #else #ifdef CONFIG_RCU_BOOST */
 
-#if !defined(CONFIG_RCU_FAST_NO_HZ)
-
-/*
- * Check to see if any future non-offloaded RCU-related work will need
- * to be done by the current CPU, even if none need be done immediately,
- * returning 1 if so.  This function is part of the RCU implementation;
- * it is -not- an exported member of the RCU API.
- *
- * Because we not have RCU_FAST_NO_HZ, just check whether or not this
- * CPU has RCU callbacks queued.
- */
-int rcu_needs_cpu(u64 basemono, u64 *nextevt)
-{
-	*nextevt = KTIME_MAX;
-	return !rcu_segcblist_empty(&this_cpu_ptr(&rcu_data)->cblist) &&
-		!rcu_rdp_is_offloaded(this_cpu_ptr(&rcu_data));
-}
-
-/*
- * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up
- * after it.
- */
-static void rcu_cleanup_after_idle(void)
-{
-}
-
-/*
- * Do the idle-entry grace-period work, which, because CONFIG_RCU_FAST_NO_HZ=n,
- * is nothing.
- */
-static void rcu_prepare_for_idle(void)
-{
-}
-
-#else /* #if !defined(CONFIG_RCU_FAST_NO_HZ) */
-
-/*
- * This code is invoked when a CPU goes idle, at which point we want
- * to have the CPU do everything required for RCU so that it can enter
- * the energy-efficient dyntick-idle mode.
- *
- * The following preprocessor symbol controls this:
- *
- * RCU_IDLE_GP_DELAY gives the number of jiffies that a CPU is permitted
- *	to sleep in dyntick-idle mode with RCU callbacks pending.  This
- *	is sized to be roughly one RCU grace period.  Those energy-efficiency
- *	benchmarkers who might otherwise be tempted to set this to a large
- *	number, be warned: Setting RCU_IDLE_GP_DELAY too high can hang your
- *	system.  And if you are -that- concerned about energy efficiency,
- *	just power the system down and be done with it!
- *
- * The value below works well in practice.  If future workloads require
- * adjustment, they can be converted into kernel config parameters, though
- * making the state machine smarter might be a better option.
- */
-#define RCU_IDLE_GP_DELAY 4		/* Roughly one grace period. */
-
-static int rcu_idle_gp_delay = RCU_IDLE_GP_DELAY;
-module_param(rcu_idle_gp_delay, int, 0644);
-
-/*
- * Try to advance callbacks on the current CPU, but only if it has been
- * awhile since the last time we did so.  Afterwards, if there are any
- * callbacks ready for immediate invocation, return true.
- */
-static bool __maybe_unused rcu_try_advance_all_cbs(void)
-{
-	bool cbs_ready = false;
-	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
-	struct rcu_node *rnp;
-
-	/* Exit early if we advanced recently. */
-	if (jiffies == rdp->last_advance_all)
-		return false;
-	rdp->last_advance_all = jiffies;
-
-	rnp = rdp->mynode;
-
-	/*
-	 * Don't bother checking unless a grace period has
-	 * completed since we last checked and there are
-	 * callbacks not yet ready to invoke.
-	 */
-	if ((rcu_seq_completed_gp(rdp->gp_seq,
-				  rcu_seq_current(&rnp->gp_seq)) ||
-	     unlikely(READ_ONCE(rdp->gpwrap))) &&
-	    rcu_segcblist_pend_cbs(&rdp->cblist))
-		note_gp_changes(rdp);
-
-	if (rcu_segcblist_ready_cbs(&rdp->cblist))
-		cbs_ready = true;
-	return cbs_ready;
-}
-
-/*
- * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready
- * to invoke.  If the CPU has callbacks, try to advance them.  Tell the
- * caller about what to set the timeout.
- *
- * The caller must have disabled interrupts.
- */
-int rcu_needs_cpu(u64 basemono, u64 *nextevt)
-{
-	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
-	unsigned long dj;
-
-	lockdep_assert_irqs_disabled();
-
-	/* If no non-offloaded callbacks, RCU doesn't need the CPU. */
-	if (rcu_segcblist_empty(&rdp->cblist) ||
-	    rcu_rdp_is_offloaded(rdp)) {
-		*nextevt = KTIME_MAX;
-		return 0;
-	}
-
-	/* Attempt to advance callbacks. */
-	if (rcu_try_advance_all_cbs()) {
-		/* Some ready to invoke, so initiate later invocation. */
-		invoke_rcu_core();
-		return 1;
-	}
-	rdp->last_accelerate = jiffies;
-
-	/* Request timer and round. */
-	dj = round_up(rcu_idle_gp_delay + jiffies, rcu_idle_gp_delay) - jiffies;
-
-	*nextevt = basemono + dj * TICK_NSEC;
-	return 0;
-}
-
-/*
- * Prepare a CPU for idle from an RCU perspective.  The first major task is to
- * sense whether nohz mode has been enabled or disabled via sysfs.  The second
- * major task is to accelerate (that is, assign grace-period numbers to) any
- * recently arrived callbacks.
- *
- * The caller must have disabled interrupts.
- */
-static void rcu_prepare_for_idle(void)
-{
-	bool needwake;
-	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
-	struct rcu_node *rnp;
-	int tne;
-
-	lockdep_assert_irqs_disabled();
-	if (rcu_rdp_is_offloaded(rdp))
-		return;
-
-	/* Handle nohz enablement switches conservatively. */
-	tne = READ_ONCE(tick_nohz_active);
-	if (tne != rdp->tick_nohz_enabled_snap) {
-		if (!rcu_segcblist_empty(&rdp->cblist))
-			invoke_rcu_core(); /* force nohz to see update. */
-		rdp->tick_nohz_enabled_snap = tne;
-		return;
-	}
-	if (!tne)
-		return;
-
-	/*
-	 * If we have not yet accelerated this jiffy, accelerate all
-	 * callbacks on this CPU.
-	 */
-	if (rdp->last_accelerate == jiffies)
-		return;
-	rdp->last_accelerate = jiffies;
-	if (rcu_segcblist_pend_cbs(&rdp->cblist)) {
-		rnp = rdp->mynode;
-		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
-		needwake = rcu_accelerate_cbs(rnp, rdp);
-		raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
-		if (needwake)
-			rcu_gp_kthread_wake();
-	}
-}
-
-/*
- * Clean up for exit from idle.  Attempt to advance callbacks based on
- * any grace periods that elapsed while the CPU was idle, and if any
- * callbacks are now ready to invoke, initiate invocation.
- */
-static void rcu_cleanup_after_idle(void)
-{
-	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
-
-	lockdep_assert_irqs_disabled();
-	if (rcu_rdp_is_offloaded(rdp))
-		return;
-	if (rcu_try_advance_all_cbs())
-		invoke_rcu_core();
-}
-
-#endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
-
 /*
  * Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the
  * grace-period kthread will do force_quiescent_state() processing?
@@ -1455,7 +1271,7 @@ static void rcu_cleanup_after_idle(void)
  * CPU unless the grace period has extended for too long.
  *
  * This code relies on the fact that all NO_HZ_FULL CPUs are also
- * CONFIG_RCU_NOCB_CPU CPUs.
+ * RCU_NOCB_CPU CPUs.
  */
 static bool rcu_nohz_full_cpu(void)
 {
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 5e2fa6fd97f1..21bebf7c9030 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -347,26 +347,6 @@ static void rcu_dump_cpu_stacks(void)
 	}
 }
 
-#ifdef CONFIG_RCU_FAST_NO_HZ
-
-static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
-{
-	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
-
-	sprintf(cp, "last_accelerate: %04lx/%04lx dyntick_enabled: %d",
-		rdp->last_accelerate & 0xffff, jiffies & 0xffff,
-		!!rdp->tick_nohz_enabled_snap);
-}
-
-#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */
-
-static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
-{
-	*cp = '\0';
-}
-
-#endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */
-
 static const char * const gp_state_names[] = {
 	[RCU_GP_IDLE] = "RCU_GP_IDLE",
 	[RCU_GP_WAIT_GPS] = "RCU_GP_WAIT_GPS",
@@ -408,13 +388,12 @@ static bool rcu_is_gp_kthread_starving(unsigned long *jp)
  * of RCU grace periods that this CPU is ignorant of, for example, "1"
  * if the CPU was aware of the previous grace period.
  *
- * Also print out idle and (if CONFIG_RCU_FAST_NO_HZ) idle-entry info.
+ * Also print out idle info.
  */
 static void print_cpu_stall_info(int cpu)
 {
 	unsigned long delta;
 	bool falsepositive;
-	char fast_no_hz[72];
 	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 	char *ticks_title;
 	unsigned long ticks_value;
@@ -432,11 +411,10 @@ static void print_cpu_stall_info(int cpu)
 		ticks_title = "ticks this GP";
 		ticks_value = rdp->ticks_this_gp;
 	}
-	print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
 	delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
 	falsepositive = rcu_is_gp_kthread_starving(NULL) &&
 			rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp));
-	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s%s\n",
+	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n",
 	       cpu,
 	       "O."[!!cpu_online(cpu)],
 	       "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
@@ -449,7 +427,6 @@ static void print_cpu_stall_info(int cpu)
 	       rdp->dynticks_nesting, rdp->dynticks_nmi_nesting,
 	       rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
 	       data_race(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart,
-	       fast_no_hz,
 	       falsepositive ? " (false positive?)" : "");
 }
 
diff --git a/kernel/scftorture.c b/kernel/scftorture.c
index 5d42f44e3e1a..dcb0410950e4 100644
--- a/kernel/scftorture.c
+++ b/kernel/scftorture.c
@@ -38,14 +38,10 @@
 #define SCFTORT_STRING "scftorture"
 #define SCFTORT_FLAG SCFTORT_STRING ": "
 
-#define SCFTORTOUT(s, x...) \
-	pr_alert(SCFTORT_FLAG s, ## x)
-
 #define VERBOSE_SCFTORTOUT(s, x...) \
-	do { if (verbose) pr_alert(SCFTORT_FLAG s, ## x); } while (0)
+	do { if (verbose) pr_alert(SCFTORT_FLAG s "\n", ## x); } while (0)
 
-#define VERBOSE_SCFTORTOUT_ERRSTRING(s, x...) \
-	do { if (verbose) pr_alert(SCFTORT_FLAG "!!! " s, ## x); } while (0)
+#define SCFTORTOUT_ERRSTRING(s, x...) pr_alert(SCFTORT_FLAG "!!! " s "\n", ## x)
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@kernel.org>");
@@ -587,14 +583,14 @@ static int __init scf_torture_init(void)
 	if (weight_resched1 == 0 && weight_single1 == 0 && weight_single_rpc1 == 0 &&
 	    weight_single_wait1 == 0 && weight_many1 == 0 && weight_many_wait1 == 0 &&
 	    weight_all1 == 0 && weight_all_wait1 == 0) {
-		VERBOSE_SCFTORTOUT_ERRSTRING("all zero weights makes no sense");
+		SCFTORTOUT_ERRSTRING("all zero weights makes no sense");
 		firsterr = -EINVAL;
 		goto unwind;
 	}
 	if (IS_BUILTIN(CONFIG_SCF_TORTURE_TEST))
 		scf_sel_add(weight_resched1, SCF_PRIM_RESCHED, false);
 	else if (weight_resched1)
-		VERBOSE_SCFTORTOUT_ERRSTRING("built as module, weight_resched ignored");
+		SCFTORTOUT_ERRSTRING("built as module, weight_resched ignored");
 	scf_sel_add(weight_single1, SCF_PRIM_SINGLE, false);
 	scf_sel_add(weight_single_rpc1, SCF_PRIM_SINGLE_RPC, true);
 	scf_sel_add(weight_single_wait1, SCF_PRIM_SINGLE, true);
@@ -625,12 +621,12 @@ static int __init scf_torture_init(void)
 		nthreads = num_online_cpus();
 	scf_stats_p = kcalloc(nthreads, sizeof(scf_stats_p[0]), GFP_KERNEL);
 	if (!scf_stats_p) {
-		VERBOSE_SCFTORTOUT_ERRSTRING("out of memory");
+		SCFTORTOUT_ERRSTRING("out of memory");
 		firsterr = -ENOMEM;
 		goto unwind;
 	}
 
-	VERBOSE_SCFTORTOUT("Starting %d smp_call_function() threads\n", nthreads);
+	VERBOSE_SCFTORTOUT("Starting %d smp_call_function() threads", nthreads);
 
 	atomic_set(&n_started, nthreads);
 	for (i = 0; i < nthreads; i++) {
diff --git a/kernel/torture.c b/kernel/torture.c
index bb8f411c974b..ef27a6c82451 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -570,7 +570,7 @@ int torture_shuffle_init(long shuffint)
 	shuffle_idle_cpu = -1;
 
 	if (!alloc_cpumask_var(&shuffle_tmp_mask, GFP_KERNEL)) {
-		VERBOSE_TOROUT_ERRSTRING("Failed to alloc mask");
+		TOROUT_ERRSTRING("Failed to alloc mask");
 		return -ENOMEM;
 	}
 
@@ -934,7 +934,7 @@ int _torture_create_kthread(int (*fn)(void *arg), void *arg, char *s, char *m,
 	*tp = kthread_run(fn, arg, "%s", s);
 	if (IS_ERR(*tp)) {
 		ret = PTR_ERR(*tp);
-		VERBOSE_TOROUT_ERRSTRING(f);
+		TOROUT_ERRSTRING(f);
 		*tp = NULL;
 	}
 	torture_shuffle_task_register(*tp);